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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 800
    Prev
    Next
    INDEX
    Explanations

    then

    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
     onCancelled
    -0.57
     pageContext
    -0.56
    Hochspringen
    -0.56
     alapján
    -0.54
    eseorang
    -0.52
     مشين
    -0.52
     متعلقه
    -0.52
    langsung
    -0.51
    actionMode
    -0.51
     Wikimedijinoj
    -0.51
    POSITIVE LOGITS
     moving
    0.78
     running
    0.73
     rotating
    0.70
     sailing
    0.69
     voting
    0.69
     racing
    0.68
     timing
    0.67
     cooking
    0.67
     loading
    0.66
     ticking
    0.66
    Activations Density 0.003%

    No Known Activations