© 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. 0-CLT-HP
    7. 95587
    Prev
    Next
    INDEX
    Explanations

    programming 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
    Negative Logits
    achi
    -1.50
    ACHI
    -1.03
     Malone
    -0.94
    клопе
    -0.57
    nest
    -0.52
     gratuits
    -0.49
    dda
    -0.46
    autant
    -0.46
    RelativePath
    -0.46
    ❉
    -0.44
    POSITIVE LOGITS
    ://$
    0.61
    URLException
    0.57
    sidemargin
    0.57
    ngths
    0.57
    minX
    0.54
    Hentet
    0.54
    tics
    0.54
    ￡
    0.53
    AutoresizingMask
    0.52
    ology
    0.52
    Activations Density 1.622%

    No Known Activations