© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12267
    Prev
    Next
    INDEX
    Explanations

    attracting attention or creating

    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
     extérieures
    -0.71
     étrangères
    -0.63
     âgées
    -0.61
     vertes
    -0.60
     représenté
    -0.60
     merve
    -0.60
     noires
    -0.56
     vectorielles
    -0.52
     privées
    -0.52
     ویکی‌پدیا
    -0.51
    POSITIVE LOGITS
     CreateTagHelper
    0.66
    cyklopedia
    0.63
    تفصیلات
    0.62
     a
    0.61
    IGraphics
    0.59
    @[+][
    0.59
    migrationBuilder
    0.59
    Numerology
    0.57
    Становништво
    0.56
    LabelTagHelper
    0.56
    Activations Density 0.004%

    No Known Activations