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. 12769
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     Kard
    -1.20
     Água
    -0.53
    getMenuInflater
    -0.52
    doGet
    -0.50
     Water
    -0.47
    gos
    -0.46
    kool
    -0.45
    بس
    -0.44
     Bullock
    -0.44
    ölk
    -0.44
    POSITIVE LOGITS
    VIAF
    0.74
     ModelExpression
    0.71
     Audiodateien
    0.63
    writeFieldEnd
    0.58
    Viitteet
    0.57
     AssemblyCulture
    0.57
    astify
    0.57
    WebVitals
    0.56
    timewa
    0.56
     VIAF
    0.56
    Activations Density 0.514%

    No Known Activations