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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4588
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable name 'e'

    python-code · gemini-2.5-flash-lite

    attribute access (negative activations)

    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
    ork
    -0.05
    (new
    -0.05
    new
    -0.05
     new
    -0.04
    rt
    -0.04
    temp
    -0.03
    old
    -0.03
    update
    -0.03
     update
    -0.03
    _values
    -0.02
    POSITIVE LOGITS
    ination
    0.13
    inations
    0.11
    ulation
    0.11
    ility
    0.10
    imum
    0.10
    ilities
    0.10
    ness
    0.10
    rence
    0.10
    enden
    0.09
    sition
    0.09
    Activations Density 100.000%

    No Known Activations