© 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

    string literal in encode/decode

    python-code · gemini-2.5-flash-lite

    call `print(` (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
     whi
    -0.04
    range
    -0.02
    .e
    -0.02
    end
    -0.02
    isited
    -0.02
     exp
    -0.01
    lace
    -0.01
    120
    -0.01
    {
    -0.01
    },
    -0.01
    Positive Logits
    ig
    0.07
    ci
    0.06
     by
    0.04
    _by
    0.04
    ines
    0.04
    inary
    0.03
    8
    0.03
     break
    0.03
    12
    0.03
    ted
    0.03
    Activations Density 95.339%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `__init__` method calls

    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
    tion
    -0.10
     temp
    -0.04
    =
    -0.04
    (re
    -0.03
     me
    -0.03
     representing
    -0.03
    dd
    -0.03
    (N
    -0.03
     else
    -0.03
    [t
    -0.03
    Positive Logits
    hor
    0.11
    es
    0.05
     mo
    0.05
     assign
    0.04
    isited
    0.04
     process
    0.04
    assign
    0.04
     ver
    0.03
    atus
    0.03
    re
    0.03
    Activations Density 6.396%

    No Known Activations