© 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. 94963
    Prev
    Next
    INDEX
    Explanations

    made

    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
     made
    -0.74
    made
    -0.69
     Made
    -0.60
     saites
    -0.60
     MADE
    -0.57
    Made
    -0.53
    MADE
    -0.47
    EDEFAULT
    -0.44
    TacToe
    -0.43
     /\.
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.65
    Diweddarwch
    0.65
     dominions
    0.58
    Chham
    0.58
     demurrer
    0.58
     ModelExpression
    0.56
     ufe
    0.56
    OwnProperty
    0.56
     mukaan
    0.56
     Saxons
    0.55
    Activations Density 0.041%

    No Known Activations