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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92378
    Prev
    Next
    INDEX
    Explanations

    groom

    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
     nakalista
    -0.84
    دانشنامهٔ
    -0.77
     '\\;'
    -0.75
     alimentaria
    -0.73
    帖最后由
    -0.73
    ViewFeatures
    -0.73
     оригіналу
    -0.72
     reaſon
    -0.72
     ciudadana
    -0.72
    enumii
    -0.72
    POSITIVE LOGITS
    s
    0.57
     box
    0.49
     vo
    0.48
     Tro
    0.48
     Ton
    0.48
    box
    0.47
    sr
    0.47
    shift
    0.46
     ban
    0.46
    shot
    0.45
    Activations Density 1.236%

    No Known Activations