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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74559
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.94
    TypedDataSet
    -0.82
     calendriers
    -0.79
    ValueStyle
    -0.77
     Wicidata
    -0.73
    AntiForgeryToken
    -0.71
     متعلقه
    -0.71
     للاسماء
    -0.70
     שוליים
    -0.70
    ьаж
    -0.70
    POSITIVE LOGITS
     how
    0.60
     human
    0.49
     predicting
    0.49
     regulating
    0.46
     measuring
    0.45
    <bos>
    0.45
     managing
    0.45
     who
    0.44
     figuring
    0.42
     promoting
    0.42
    Activations Density 0.000%

    No Known Activations