© 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. 0-CLT-HP
    7. 45105
    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
    ismic
    -1.59
    Hozzáférés
    -0.74
    WebVitals
    -0.60
    VersionUID
    -0.58
     محفوظة
    -0.58
    ineno
    -0.57
    TextAppearance
    -0.56
     Erişim
    -0.53
    Népesség
    -0.53
     lenker
    -0.52
    POSITIVE LOGITS
    rungsseite
    0.58
    այ
    0.55
     zod
    0.54
    poxy
    0.53
     zusammenge
    0.53
    PerSecond
    0.53
     становника
    0.52
    IVEREF
    0.52
    othelioma
    0.52
    ynchro
    0.51
    Activations Density 0.042%

    No Known Activations