© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96317
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     Мексичка
    -0.91
    AddTagHelper
    -0.84
     continúas
    -0.73
    antaranya
    -0.73
    __':
    -0.71
     fieldNum
    -0.71
    saraba
    -0.70
     HttpNotFound
    -0.69
    __':
    -0.68
     ویکی‌پدیای
    -0.68
    POSITIVE LOGITS
     the
    0.57
     animals
    0.50
     Based
    0.48
    once
    0.47
     cholesterol
    0.46
     based
    0.45
    Based
    0.45
     once
    0.45
    Think
    0.44
     mutations
    0.43
    Activations Density 0.001%

    No Known Activations