© 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. 0-CLT-HP
    7. 95093
    Prev
    Next
    INDEX
    Explanations

    rep

    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
     rep
    -0.86
     reps
    -0.80
     surprises
    -0.75
     transfieras
    -0.72
     surprising
    -0.67
    representation
    -0.66
     FormData
    -0.65
     surprise
    -0.65
    UVWXYZ
    -0.64
     repetition
    -0.63
    POSITIVE LOGITS
     Waray
    0.56
    eks
    0.56
    روابط
    0.54
    ActiveRecord
    0.51
     himſelf
    0.50
    bibitem
    0.48
     Phry
    0.48
     Pleistocene
    0.47
    ities
    0.47
    الصفحه
    0.47
    Activations Density 0.071%

    No Known Activations