© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma separated arguments

    python-code · gemini-2.5-flash-lite

    class definition or method parameters (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .parent
    -0.02
    hildren
    -0.02
    ameters
    -0.02
    structions
    -0.02
     !=
    -0.01
     parent
    -0.01
    endencies
    -0.01
    No
    -0.01
     prev
    -0.01
    ner
    -0.01
    Positive Logits
     raise
    0.05
     continue
    0.04
     while
    0.04
     break
    0.04
     else
    0.04
     elif
    0.03
    print
    0.03
     print
    0.03
     return
    0.03
     if
    0.02
    Activations Density 99.303%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    numpy.linalg.norm or np.linalg.norm

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    arent
    -0.09
     parent
    -0.05
    un
    -0.03
    ighbor
    -0.02
    ighbour
    -0.02
    (i
    -0.01
    (row
    -0.01
    ath
    -0.01
    (x
    -0.01
     pre
    -0.01
    Positive Logits
    or
    0.06
     ny
    0.04
    y
    0.03
     input
    0.03
     dy
    0.03
    osition
    0.03
    Y
    0.03
     Y
    0.03
    _of
    0.03
    label
    0.03
    Activations Density 8.433%

    No Known Activations