© 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. 97741
    Prev
    Next
    INDEX
    Explanations

    supp

    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
     Promote
    -0.99
     promote
    -0.90
    promote
    -0.87
     promoting
    -0.84
    Promote
    -0.84
     promotion
    -0.84
     Promotion
    -0.77
     Promoting
    -0.76
     promoted
    -0.72
    promoting
    -0.71
    POSITIVE LOGITS
     plainte
    0.55
    YourGuide
    0.53
     TMPro
    0.52
     eccell
    0.50
     avrebbero
    0.48
    ietal
    0.48
     competen
    0.48
     précie
    0.48
    ‍♀️
    0.47
     stesse
    0.47
    Activations Density 0.030%

    No Known Activations