© 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. 5-CLT-HP
    7. 97254
    Prev
    Next
    INDEX
    Explanations

    Garden

    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
    Atsauces
    -0.67
    itzender
    -0.65
     poveznice
    -0.58
    hyrchwyd
    -0.56
    MLLoader
    -0.56
     ✓
    -0.55
    transQ
    -0.54
     navideñas
    -0.54
     Chair
    -0.54
     وصلة
    -0.54
    POSITIVE LOGITS
    énario
    0.56
    styleUrls
    0.53
    awtextra
    0.52
    inkas
    0.48
     оригіналу
    0.48
    ics
    0.47
    ẽ
    0.46
    $_['
    0.44
    weiten
    0.44
    oneph
    0.44
    Activations Density 0.006%

    No Known Activations