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. 11118
    Prev
    Next
    INDEX
    Explanations

    Unstructured internet text snippets

    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
    on
    -0.47
    arm
    -0.46
    ar
    -0.45
    case
    -0.44
    ang
    -0.44
    ket
    -0.44
    in
    -0.42
     moves
    -0.41
    ate
    -0.41
    ros
    -0.41
    POSITIVE LOGITS
     незавершена
    0.67
     insuffisamment
    0.65
     BrowserModule
    0.65
    Бахар
    0.63
    ніципалі
    0.62
    lgari
    0.62
    Демографія
    0.60
     Answering
    0.59
    商品説明
    0.58
     noqa
    0.58
    Activations Density 0.020%

    No Known Activations