© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1400
    Prev
    Next
    INDEX
    Explanations

    self prefix and attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    `self` parameter in methods

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
    losest
    -0.14
    _st
    -0.09
    (st
    -0.08
     st
    -0.04
     closest
    -0.04
    ch
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    ransition
    0.33
    (state
    0.23
     state
    0.21
    _state
    0.21
    _states
    0.20
    cept
    0.12
    mbol
    0.09
    bab
    0.08
    cep
    0.08
    ach
    0.07
    Activations Density 100.000%

    No Known Activations