© 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. 71364
    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
    HandlerContext
    -0.77
    DeleteBehavior
    -0.76
    AndEndTag
    -0.73
    Portale
    -0.73
    VIAF
    -0.71
    TagMode
    -0.70
     numerus
    -0.69
     الحره
    -0.69
    AnchorStyles
    -0.68
    UnusedPrivate
    -0.67
    POSITIVE LOGITS
     اكتوبر
    0.43
     $
    0.43
     Air
    0.42
    ärä
    0.41
     shot
    0.41
     krav
    0.40
     kit
    0.39
     sost
    0.39
    ár
    0.39
     обращения
    0.39
    Activations Density 0.000%

    No Known Activations