© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45790
    Prev
    Next
    INDEX
    Explanations

    transparent

    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
     الحره
    -0.78
    AddTagHelper
    -0.73
     صوتيه
    -0.70
     وتسجيلات
    -0.66
    出版年
    -0.57
    GEBURTSDATUM
    -0.56
     Réponses
    -0.56
     OnInit
    -0.54
     wrest
    -0.54
     Lieberman
    -0.54
    POSITIVE LOGITS
     createSprite
    0.57
    المكان
    0.56
    hips
    0.52
    cedent
    0.50
    qrstuvwxyz
    0.48
    ysacchar
    0.48
    "]))
    0.47
    ndata
    0.47
    ess
    0.46
    Примеча
    0.46
    Activations Density 0.126%

    No Known Activations