© 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
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72764
    Prev
    Next
    INDEX
    Explanations

    say "respectively"

    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
    however
    -1.13
    ,
    -1.10
     entanto
    -1.04
    Consequently
    -1.02
    donc
    -1.01
     scolaires
    -0.99
    Accordingly
    -0.96
    therefore
    -0.96
    However
    -0.94
     perciò
    -0.94
    POSITIVE LOGITS
     للمعارف
    0.45
     تانيه
    0.40
    WIG
    0.39
     GoogleFonts
    0.36
    Revenir
    0.36
    @[
    0.35
    WriteAttribute
    0.35
    \/
    0.35
    ...@
    0.33
     Wars
    0.33
    Activations Density 0.003%

    No Known Activations