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. 11042
    Prev
    Next
    INDEX
    Explanations

    this

    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
    CloseOperation
    -0.68
    Coordonnées
    -0.60
    +#+
    -0.53
    '");
    -0.53
    ponses
    -0.51
     vora
    -0.51
    GraphicsUnit
    -0.49
    _));
    -0.48
    '
    
    -0.47
    mtp
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.64
    addCriterion
    0.60
     GenerationType
    0.54
    KommentareTeilen
    0.54
    casio
    0.53
    contentLoaded
    0.53
    COW
    0.52
    addTab
    0.51
    lamabad
    0.51
    клопе
    0.51
    Activations Density 0.004%

    No Known Activations