© 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. 660
    Prev
    Next
    INDEX
    Explanations

    code/numbers/routes

    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
     transfé
    -0.56
     duquel
    -0.55
    jsonwebtoken
    -0.53
     surla
    -0.53
     keras
    -0.49
    ague
    -0.48
    Демографія
    -0.46
    titleMargin
    -0.46
     jsPsych
    -0.46
    setNext
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.85
    onAttach
    0.64
    astify
    0.56
     Италијани
    0.52
     Horatio
    0.52
     apologise
    0.50
     InputDecoration
    0.49
    клопе
    0.49
     Chwiliwch
    0.49
    ApiModel
    0.49
    Activations Density 0.005%

    No Known Activations