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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95991
    Prev
    Next
    INDEX
    Explanations

    statements of advice/obligation

    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
    protoimpl
    -0.82
     ModelExpression
    -0.69
     resourceCulture
    -0.65
     Waray
    -0.64
    Hentet
    -0.59
    tagext
    -0.57
    IsMutable
    -0.54
     BitmapFactory
    -0.54
    ValueGenerated
    -0.53
    mtrl
    -0.52
    POSITIVE LOGITS
     Exciting
    0.64
    Exciting
    0.62
     fun
    0.59
     initComponents
    0.55
     excitement
    0.54
     exciting
    0.53
     عنها
    0.53
    ออกมา
    0.52
    enrich
    0.52
     enjoyed
    0.51
    Activations Density 0.002%

    No Known Activations