Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12749
    Prev
    Next
    INDEX
    Explanations

    Wil

    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
    er
    -0.56
    or
    -0.47
     in
    -0.44
    箱
    -0.43
     חיצוניים
    -0.43
    ers
    -0.42
     box
    -0.42
     by
    -0.42
     for
    -0.42
     after
    -0.42
    POSITIVE LOGITS
     وتسجيلات
    0.84
    ftagPool
    0.82
     AssemblyProduct
    0.79
     itſelf
    0.77
    matchCondition
    0.76
     feroit
    0.75
     الرياضيه
    0.73
     gyhoeddwyd
    0.73
     للمعارف
    0.71
     myſelf
    0.71
    Activations Density 0.026%

    No Known Activations