© 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. 91050
    Prev
    Next
    INDEX
    Explanations

    assistance

    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
    RenderAtEndOf
    -0.52
     one
    -0.50
    astify
    -0.49
     للاسماء
    -0.49
     فريبيس
    -0.46
    Point
    -0.45
    wyżs
    -0.45
    ConstraintMaker
    -0.44
    uali
    -0.43
    期刊论文
    -0.41
    POSITIVE LOGITS
    IndentedString
    0.75
     help
    0.73
    !("{}",
    0.66
    клопе
    0.64
    mybatisplus
    0.61
    help
    0.60
    Zeneca
    0.60
     GLC
    0.60
    enoord
    0.59
    хьтан
    0.58
    Activations Density 0.021%

    No Known Activations