© 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. 8886
    Prev
    Next
    INDEX
    Explanations

    working

    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
    Externí
    -0.50
     pregunto
    -0.49
     quelcon
    -0.49
    Odkazy
    -0.46
    égories
    -0.44
     hvil
    -0.44
     quelconque
    -0.44
    atissimo
    -0.43
     fallu
    -0.42
    InstanceState
    -0.42
    POSITIVE LOGITS
    transQ
    0.70
    addCriterion
    0.68
     kasarigan
    0.67
    yntaxException
    0.66
    Tikang
    0.63
     Parties
    0.59
    RectangleBorder
    0.58
     Bentham
    0.56
    GMENT
    0.56
     retriever
    0.55
    Activations Density 0.013%

    No Known Activations