© 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. 38800
    Prev
    Next
    INDEX
    Explanations

    institutional

    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
    rrggbb
    -1.02
    providedIn
    -0.91
     Paglinawan
    -0.89
     Мексичка
    -0.87
     ostavi
    -0.87
    expandindo
    -0.87
     للاسماء
    -0.86
     GenerationType
    -0.85
    protoimpl
    -0.85
    URLException
    -0.84
    POSITIVE LOGITS
    ism
    0.74
    ist
    0.71
    ise
    0.66
    ization
    0.66
    ists
    0.61
    ized
    0.55
    ake
    0.52
    idad
    0.50
     habitudes
    0.49
    ion
    0.48
    Activations Density 0.067%

    No Known Activations