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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13457
    Prev
    Next
    INDEX
    Explanations

    security

    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
     الرياضيه
    -0.60
     ModelExpression
    -0.56
    béco
    -0.55
    findpost
    -0.53
     unsafe
    -0.51
    出版年
    -0.51
     Lordships
    -0.50
    InSection
    -0.48
    providedIn
    -0.48
    BeforeMethod
    -0.48
    POSITIVE LOGITS
     Efq
    0.56
    $")
    0.52
    pressing
    0.50
    %");
    0.48
    İstinadlar
    0.48
    enya
    0.46
    Garantie
    0.46
    ſhip
    0.45
    لينكات
    0.45
    neſs
    0.45
    Activations Density 0.022%

    No Known Activations