© 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. 78204
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     disambiguazione
    -0.72
    Tikang
    -0.65
    AndEndTag
    -0.62
     للاسماء
    -0.61
     JScrollPane
    -0.56
    ToBounds
    -0.55
    archiviato
    -0.55
    Personensuche
    -0.54
    jsii
    -0.54
     DialogInterface
    -0.52
    POSITIVE LOGITS
    <_>
    0.54
    Packard
    0.52
    AppCompatTheme
    0.51
    phonie
    0.49
    Tim
    0.47
    afficheront
    0.47
    DBObject
    0.46
     Tim
    0.46
    ầng
    0.45
    celess
    0.44
    Activations Density 0.002%

    No Known Activations