© 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. 45606
    Prev
    Next
    INDEX
    Explanations

    part

    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
    族館
    -0.51
     kanyang
    -0.50
    mintaan
    -0.50
    värr
    -0.49
     Reptile
    -0.48
     Dinosaur
    -0.47
    ed
    -0.45
    SEPARATOR
    -0.45
     Turtle
    -0.45
     CGFloat
    -0.43
    POSITIVE LOGITS
    lably
    0.56
    ngOn
    0.56
    الحياه
    0.53
     للاسماء
    0.53
    앵
    0.52
    ArgsConstructor
    0.52
     "}";
    0.51
     vivement
    0.51
    ︎
    0.50
    ctiv
    0.50
    Activations Density 0.006%

    No Known Activations