© 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. 94074
    Prev
    Next
    INDEX
    Explanations

    bytes

    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
    tagHelperRunner
    -0.90
    Atsauces
    -0.84
     connexe
    -0.73
    ">//
    -0.71
    bytes
    -0.70
    Viited
    -0.70
     bytes
    -0.68
    Искәрмәләр
    -0.68
     ligiloj
    -0.65
     Connected
    -0.65
    POSITIVE LOGITS
     createContext
    0.42
    TemporalType
    0.39
    plish
    0.39
    LY
    0.38
    W
    0.38
     pra
    0.38
    jst
    0.38
     Sp
    0.37
    дри
    0.37
    Clo
    0.36
    Activations Density 0.880%

    No Known Activations