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. 20-CLT-HP
    4. 74079
    Prev
    Next
    INDEX
    Explanations

    Foreign/technical terms

    np_max-act-logits · 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
    AndEndTag
    -0.51
    EndContext
    -0.47
    NameInMap
    -0.47
     exiles
    -0.45
     blows
    -0.45
     DialogInterface
    -0.45
     Heinemann
    -0.44
     liquids
    -0.43
     products
    -0.43
    帖最后由
    -0.42
    POSITIVE LOGITS
     المعيارى
    0.73
     виправивши
    0.60
     Baillargeon
    0.60
    참고
    0.59
    IntoConstraints
    0.59
     autorytatywna
    0.57
    DoubleQuotes
    0.54
    calciatore
    0.54
     مشين
    0.53
    UIControlState
    0.53
    Activations Density 0.000%

    No Known Activations