© 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. 71339
    Prev
    Next
    INDEX
    Explanations

    technical information

    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
    riwal
    -0.55
    OOTDTY
    -0.54
     Wikimedijinoj
    -0.54
    jandra
    -0.54
     dovuto
    -0.50
    utives
    -0.50
    requipa
    -0.49
     HttpNotFound
    -0.49
    íritu
    -0.49
    lok
    -0.49
    POSITIVE LOGITS
     ujednoznacz
    0.67
    rungsseite
    0.57
    msgTypes
    0.57
     بيها
    0.56
     createState
    0.55
     StatefulWidget
    0.55
     ivelany
    0.55
    TagMode
    0.52
    Géographie
    0.50
     صوتيه
    0.50
    Activations Density 0.000%

    No Known Activations