© 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. 1-CLT-HP
    7. 304
    Prev
    Next
    INDEX
    Explanations

    covers

    np_max-act · gemini-2.0-flash
    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
     épaules
    -0.53
     lunak
    -0.51
     lèvres
    -0.51
     oídos
    -0.49
    发表于
    -0.49
     tebal
    -0.49
     COVER
    -0.48
     CURIAM
    -0.48
     proposito
    -0.47
     covers
    -0.45
    POSITIVE LOGITS
     the
    0.75
     BoxDecoration
    0.75
     Paglinawan
    0.73
    Gambas
    0.71
     an
    0.69
     متعلقه
    0.67
     للاسماء
    0.67
     a
    0.66
    BeginContext
    0.66
     समीक्षाओं
    0.66
    Activations Density 0.012%

    No Known Activations