Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 510
    Prev
    Next
    INDEX
    Explanations

    first

    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
    anskje
    -0.64
    Referències
    -0.63
    canActivate
    -0.60
    apimachinery
    -0.59
    EndContext
    -0.58
     arşivlendi
    -0.58
     nakalista
    -0.57
    latego
    -0.57
    uxxxx
    -0.56
    ########.
    -0.56
    POSITIVE LOGITS
    httphttps
    0.59
    ing
    0.54
    onedDateTime
    0.52
    ukkah
    0.50
    ments
    0.50
    })`
    0.48
    URLException
    0.48
    stood
    0.47
    eradish
    0.47
    ness
    0.47
    Activations Density 0.063%

    No Known Activations