© 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. 20-CLT-HP
    7. 76480
    Prev
    Next
    INDEX
    Explanations

    second

    np_max-act-logits · 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
     autorytatywna
    -0.89
    IsMutable
    -0.77
    InitVars
    -0.74
    AndEndTag
    -0.73
    protoimpl
    -0.70
    ArrowToggle
    -0.70
    SBATCH
    -0.69
    memoized
    -0.67
    SharedCtor
    -0.66
     архивлан
    -0.65
    POSITIVE LOGITS
     Sec
    0.91
     sec
    0.84
    Sec
    0.84
    sec
    0.79
     seconds
    0.78
    SEC
    0.70
     se
    0.67
     SEC
    0.64
     Se
    0.57
     sek
    0.57
    Activations Density 0.018%

    No Known Activations