© 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. 13014
    Prev
    Next
    INDEX
    Explanations

    code

    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
    AsUp
    -1.04
     propOrder
    -0.86
     оригіналу
    -0.76
     ComVisible
    -0.71
    IonicModule
    -0.68
     Мексичка
    -0.68
    Geplaatst
    -0.68
     ویکی‌پدی
    -0.67
     دیکھیے
    -0.66
     ویکی‌پدیا
    -0.66
    POSITIVE LOGITS
    OIR
    0.51
    SuspendLayout
    0.48
    coma
    0.47
     thế
    0.47
    ensk
    0.46
     unique
    0.46
     aé
    0.46
    ⎩
    0.45
     denn
    0.45
    cupertino
    0.45
    Activations Density 0.433%

    No Known Activations