© 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. 4-CLT-HP
    7. 623
    Prev
    Next
    INDEX
    Explanations

    case

    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
    CopyWith
    -0.64
     saites
    -0.60
    problemas
    -0.57
     prêts
    -0.54
     RequestMethod
    -0.52
     @"/
    -0.50
     réalisés
    -0.50
    UIControlState
    -0.50
    ########.
    -0.48
    Viited
    -0.47
    POSITIVE LOGITS
    lessly
    0.63
    Surge
    0.53
    ositol
    0.53
     fatale
    0.51
    يكب
    0.51
    onuc
    0.50
    kháu
    0.49
    pexpr
    0.49
    atically
    0.48
    참고
    0.48
    Activations Density 0.010%

    No Known Activations