© 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

    math functions followed by opening parenthesis

    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
    py
    -0.08
    dule
    -0.07
    uil
    -0.06
     sys
    -0.04
     code
    -0.04
     {}↵↵
    -0.04
     run
    -0.04
    gorithm
    -0.04
    ases
    -0.03
     sc
    -0.03
    Positive Logits
    uples
    0.06
    uple
    0.06
    adjac
    0.05
    uccess
    0.04
     conne
    0.04
    ab
    0.03
    duct
    0.03
    qrt
    0.03
     abs
    0.03
    ag
    0.03
    Activations Density 59.102%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list method calls after variable (negative activations)

    python-code · gemini-2.5-flash-lite

    import `random` or `math`

    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
    (N
    -0.08
    qrt
    -0.07
    (len
    -0.07
    (map
    -0.05
    idth
    -0.04
    reshold
    -0.04
     x
    -0.04
    _size
    -0.04
    _len
    -0.04
    len
    -0.04
    Positive Logits
    atus
    0.07
    ost
    0.06
     conne
    0.05
    _for
    0.05
    200
    0.05
     spe
    0.04
     re
    0.03
    ).
    0.03
    form
    0.03
    ut
    0.03
    Activations Density 99.528%

    No Known Activations