© 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. 39889
    Prev
    Next
    INDEX
    Explanations

    Forces

    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
     Forces
    -0.84
    chymal
    -0.82
    __":
    -0.79
    KURZBESCHREIBUNG
    -0.73
    __':
    -0.68
    
    -0.68
     مرئيه
    -0.66
    olesale
    -0.64
    inderella
    -0.63
    NewLabel
    -0.63
    POSITIVE LOGITS
    er
    0.61
    en
    0.61
    t
    0.57
    AndroidJUnit
    0.55
    n
    0.51
    l
    0.51
    клопе
    0.50
     typelib
    0.50
    sm
    0.50
    enko
    0.50
    Activations Density 0.133%

    No Known Activations