© 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

    isapha method

    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
    reshold
    -0.05
    ange
    -0.04
    ents
    -0.04
    ency
    -0.04
    ain
    -0.04
    en
    -0.03
    ent
    -0.03
    rib
    -0.03
    rom
    -0.03
    ault
    -0.02
    Positive Logits
    uples
    0.06
    uple
    0.06
    ab
    0.04
    qrt
    0.03
     abs
    0.03
    mbol
    0.03
     tuple
    0.03
    lit
    0.02
     Tuple
    0.02
    orted
    0.02
    Activations Density 90.436%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable return value

    python-code · gemini-2.5-flash-lite

    keyword colon followed by code block (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
     :
    -0.02
    -
    -0.02
    (file
    -0.02
     -
    -0.02
     enumerate
    -0.01
     file
    -0.01
    .de
    -0.01
    :
    -0.01
     dist
    -0.01
     distances
    -0.01
    Positive Logits
     it
    0.05
    qrt
    0.03
     Create
    0.03
    itial
    0.03
    .append
    0.03
     defaultdict
    0.02
     -=
    0.02
    stance
    0.02
    .remove
    0.02
    .add
    0.02
    Activations Density 97.038%

    No Known Activations