© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 76362
    Prev
    Next
    INDEX
    Explanations

    say "of"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ZoneId
    -0.51
     sulla
    -0.48
    новить
    -0.44
     zur
    -0.44
     muualla
    -0.44
     समीक्षाओं
    -0.43
    ложений
    -0.43
    arki
    -0.42
    TagHelper
    -0.42
     for
    -0.42
    POSITIVE LOGITS
     of
    2.00
     của
    1.04
    ของ
    0.95
    of
    0.81
     Of
    0.80
    Of
    0.73
    OfThe
    0.66
     ofthe
    0.66
     ของ
    0.64
     των
    0.62
    Activations Density 0.013%

    No Known Activations