© 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. 1-CLT-HP
    7. 12980
    Prev
    Next
    INDEX
    Explanations

    draw

    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
     draw
    -0.94
     drawing
    -0.93
     Drawing
    -0.89
    Drawing
    -0.84
    draw
    -0.84
     draws
    -0.84
    Draw
    -0.80
     drew
    -0.79
     Draw
    -0.76
    drawing
    -0.72
    POSITIVE LOGITS
     Superhost
    0.66
     Monfieur
    0.66
    تفصیلات
    0.63
     referenties
    0.59
    IUrlHelper
    0.59
     Oso
    0.58
     Perci
    0.57
     jati
    0.56
     jedi
    0.55
     Tapa
    0.55
    Activations Density 0.011%

    No Known Activations