© 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. 1-CLT-HP
    7. 14842
    Prev
    Next
    INDEX
    Explanations

    random facts

    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
    ">//
    -0.69
    ագրություններ
    -0.60
     rospy
    -0.57
     joaat
    -0.57
    UserScript
    -0.56
    aarrggbb
    -0.54
    trato
    -0.49
     Ruta
    -0.49
    escaping
    -0.47
     jScrollPane
    -0.46
    POSITIVE LOGITS
    devamını
    0.60
    balleur
    0.52
     &[
    0.51
    :✨
    0.50
     around
    0.50
     démocr
    0.49
     écout
    0.49
    VersionUID
    0.48
    참고
    0.47
     subterrá
    0.46
    Activations Density 0.004%

    No Known Activations