© 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. 0-CLT-HP
    7. 94920
    Prev
    Next
    INDEX
    Explanations

    Video contents

    np_max-act · 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
     
    -0.68
     Video
    -0.60
     V
    -0.60
     video
    -0.56
     (
    -0.54
     The
    -0.54
    let
    -0.53
     he
    -0.52
     c
    -0.52
     h
    -0.50
    POSITIVE LOGITS
     Houſe
    1.09
     Efq
    1.02
     ་་
    0.98
     ―――――
    0.97
     itſelf
    0.97
    ſelf
    0.95
    Personendaten
    0.95
     Anſ
    0.93
    ArgsConstructor
    0.92
    Portail
    0.90
    Activations Density 1.364%

    No Known Activations