© 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. 20-CLT-HP
    7. 71426
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
    GraphicsUnit
    -0.52
    ’
    -0.47
    Rohy
    -0.44
    #+#
    -0.44
    numerusform
    -0.43
     EClass
    -0.42
     astore
    -0.41
    <bos>
    -0.41
     nakalista
    -0.41
     dass
    -0.39
    POSITIVE LOGITS
     vôtre
    0.73
    ystem
    0.68
     armée
    0.68
     dignité
    0.67
    ParallelGroup
    0.67
     rivista
    0.65
     autorité
    0.65
    cales
    0.63
    helves
    0.63
     contenuti
    0.63
    Activations Density 0.003%

    No Known Activations