© 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. 74594
    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
     MainAxisSize
    -0.50
     ModelExpression
    -0.44
     Diag
    -0.44
    ioutil
    -0.43
    ZE
    -0.43
     StringTokenizer
    -0.42
    eload
    -0.42
     Instrum
    -0.41
    ua
    -0.41
    eca
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.94
     للاسماء
    0.79
    Derbyniad
    0.70
     Italijanski
    0.68
     allAfrica
    0.66
     estekak
    0.65
     ExecuteAsync
    0.63
     neceff
    0.63
     reaſon
    0.62
     متعلقه
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.