© 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. 15882
    Prev
    Next
    INDEX
    Explanations

    am/em

    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
    GEBURTSDATUM
    -0.72
    BibitemShut
    -0.52
    +#+#
    -0.52
     szab
    -0.50
     fumée
    -0.49
     bénéfices
    -0.48
    Населення
    -0.47
    sted
    -0.45
     kostenlosen
    -0.45
    kiwa
    -0.44
    POSITIVE LOGITS
    <?
    0.77
     nakalista
    0.71
     للمعارف
    0.70
    !*\
    0.66
    
    0.65
    intios
    0.65
    Tikang
    0.63
    клопе
    0.63
    MENAFN
    0.63
    InvalidProtocol
    0.62
    Activations Density 0.037%

    No Known Activations