© 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

    @ decorators and def statements

    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
     \
    -0.07
     /
    -0.05
     main
    -0.03
    /
    -0.03
     x
    -0.02
    (y
    -0.01
    (map
    -0.01
     pi
    -0.01
     y
    -0.01
    .
    -0.01
    Positive Logits
     },↵
    0.07
    def
    0.07
    class
    0.06
    @
    0.05
    0.05
     ]↵
    0.04
     def
    0.04
     {'
    0.03
     {"
    0.03
     }↵
    0.03
    Activations Density 31.646%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class inheriting from object

    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
    mo
    -0.10
    isi
    -0.07
    liver
    -0.06
    sert
    -0.06
    endencies
    -0.06
    enden
    -0.05
    la
    -0.04
    que
    -0.04
    ta
    -0.04
    gree
    -0.03
    Positive Logits
    dint
    0.10
    ):
    0.07
    di
    0.07
    inal
    0.06
    join
    0.06
    T
    0.06
    lable
    0.04
    16
    0.03
    stance
    0.03
     t
    0.02
    Activations Density 36.465%

    No Known Activations