© 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. 0-CLT-HP
    7. 40231
    Prev
    Next
    INDEX
    Explanations

    what something implies

    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
     démocr
    -0.69
    aarrggbb
    -0.64
     élas
    -0.63
     étoit
    -0.61
     conseguenze
    -0.58
     complètes
    -0.57
     arbete
    -0.56
     normaux
    -0.56
     cioè
    -0.55
     économiques
    -0.55
    POSITIVE LOGITS
    出版年
    0.64
     Infórmanos
    0.63
    허
    0.54
     Denver
    0.54
    SuppressMessage
    0.53
     بيها
    0.52
    <bos>
    0.50
     let
    0.49
     way
    0.49
    âce
    0.49
    Activations Density 0.156%

    No Known Activations