© 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. 0-CLT-HP
    7. 91176
    Prev
    Next
    INDEX
    Explanations

    some

    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
    ams
    -0.57
     reproduction
    -0.53
     some
    -0.49
    ,
    -0.46
     a
    -0.46
     Dorf
    -0.45
    lets
    -0.45
    lish
    -0.44
    грам
    -0.43
    NAM
    -0.43
    POSITIVE LOGITS
     conmigo
    0.77
    CloseOperation
    0.76
     BoxFit
    0.76
     kaynağından
    0.72
     '\\;'
    0.71
     gånger
    0.69
     deschis
    0.69
    تقاوى
    0.68
     ویکی‌پدیا
    0.68
    GEBURTSDATUM
    0.68
    Activations Density 0.757%

    No Known Activations