© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10820
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    TintMode
    -0.64
    ArrowToggle
    -0.59
    -
    -0.55
     GenerationType
    -0.54
    ("$.
    -0.52
     nonatomic
    -0.50
     AspNetCore
    -0.47
    RTLD
    -0.47
    ForValue
    -0.47
    roveň
    -0.46
    POSITIVE LOGITS
    sheets
    0.67
    sheet
    0.61
    帖最后由
    0.59
    shaft
    0.57
    steps
    0.56
    screen
    0.54
    step
    0.54
    shell
    0.53
    sho
    0.53
    soup
    0.53
    Activations Density 0.066%

    No Known Activations