© 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. 4-CLT-HP
    7. 4335
    Prev
    Next
    INDEX
    Explanations

    fatal/lethal

    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
    Obrázky
    -0.95
    LookAnd
    -0.87
     autorytatywna
    -0.77
    Datuak
    -0.77
    Šaltiniai
    -0.73
    QMetaType
    -0.72
    帖最后由
    -0.71
     Audiodateien
    -0.71
    Geplaatst
    -0.68
     насељу
    -0.68
    POSITIVE LOGITS
    istic
    0.58
     outcome
    0.52
    ISTIC
    0.48
    isty
    0.46
     danger
    0.46
    itous
    0.43
    endfor
    0.43
     outcomes
    0.42
     dosis
    0.42
    lict
    0.42
    Activations Density 0.006%

    No Known Activations