© 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. 4328
    Prev
    Next
    INDEX
    Explanations

    addiction

    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
    EndInit
    -0.72
    CPtr
    -0.66
     متعلقه
    -0.59
    chyma
    -0.57
    PerformLayout
    -0.57
    WebVitals
    -0.57
    الإنجليزية
    -0.56
     encar
    -0.52
    tead
    -0.52
    PhysRev
    -0.52
    POSITIVE LOGITS
     to
    1.40
     liability
    0.63
     rates
    0.63
     thereto
    0.63
     toa
    0.59
    tothe
    0.58
    ToObject
    0.55
     potential
    0.55
    to
    0.54
     να
    0.54
    Activations Density 0.002%

    No Known Activations