© 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. 5-CLT-HP
    7. 91976
    Prev
    Next
    INDEX
    Explanations

    Web code and names

    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
    oredCriteria
    -0.57
    expandindo
    -0.55
     архивлан
    -0.51
    Rcpp
    -0.51
     HasFactory
    -0.51
     lenker
    -0.50
     uLocal
    -0.49
    !*\
    -0.49
    GraphicsUnit
    -0.48
    utnik
    -0.48
    POSITIVE LOGITS
    UnknownFields
    0.61
     RIPRODUZIONE
    0.60
    ofern
    0.60
    BagLayout
    0.57
     overnight
    0.54
    manha
    0.50
     engineer
    0.50
     Engineer
    0.50
    SequentialGroup
    0.49
     Pease
    0.49
    Activations Density 0.002%

    No Known Activations