© 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. 4-CLT-HP
    7. 4649
    Prev
    Next
    INDEX
    Explanations

    adjectives

    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
     only
    -0.60
     more
    -0.58
    tség
    -0.54
    hoga
    -0.54
    Only
    -0.53
     MORE
    -0.52
    ilions
    -0.51
     Haupts
    -0.50
     mostly
    -0.50
    hips
    -0.50
    POSITIVE LOGITS
    SerializedSize
    0.57
     then
    0.57
     that
    0.56
     today
    0.53
    LookAnd
    0.52
    évaluateur
    0.51
     to
    0.49
    出版年
    0.49
    ówczas
    0.49
     now
    0.49
    Activations Density 0.006%

    No Known Activations