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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11193
    Prev
    Next
    INDEX
    Explanations

    aspect

    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
     otomatig
    -0.75
    GEBURTSDATUM
    -0.70
     للمعارف
    -0.69
     AssemblyCompany
    -0.66
    toggler
    -0.63
    migrationBuilder
    -0.63
    TintMode
    -0.63
    expandindo
    -0.63
    енча
    -0.63
    CloseOperation
    -0.63
    POSITIVE LOGITS
    CTP
    0.55
    <bos>
    0.53
    NDC
    0.52
    PRC
    0.49
    cloudfront
    0.48
    DoubleQuotes
    0.47
    CAPE
    0.46
     Tahu
    0.44
     Senegal
    0.44
     giving
    0.44
    Activations Density 0.024%

    No Known Activations