© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8740
    Prev
    Next
    INDEX
    Explanations

    anatomy

    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
    Negative Logits
     sottile
    -0.62
     termica
    -0.57
     Deuteronomy
    -0.53
     behö
    -0.51
     adatt
    -0.50
     pitié
    -0.47
     diría
    -0.46
    ształ
    -0.46
     skydd
    -0.45
    Deuter
    -0.44
    POSITIVE LOGITS
    queryInterface
    0.84
    ArrowToggle
    0.68
    下载附件
    0.68
    sizeCache
    0.63
     autorytatywna
    0.63
    ANTLR
    0.60
    Rüyada
    0.60
     propOrder
    0.59
    LEncoder
    0.59
    transQ
    0.57
    Activations Density 0.006%

    No Known Activations