© 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. 2459
    Prev
    Next
    INDEX
    Explanations

    tor

    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
    HtmlAttribute
    -0.77
    //
    -0.64
    tonode
    -0.60
     مشين
    -0.60
    expandindo
    -0.59
    帖最后由
    -0.59
     estiver
    -0.54
     iprot
    -0.53
    юрпри
    -0.52
    EDEFAULT
    -0.52
    POSITIVE LOGITS
    STOR
    0.53
    SerializedSize
    0.52
    tető
    0.48
     lenker
    0.48
    xid
    0.48
    Revenir
    0.47
     Audiodateien
    0.47
     Journeys
    0.47
     bander
    0.46
    trab
    0.46
    Activations Density 0.055%

    No Known Activations