© 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. 94361
    Prev
    Next
    INDEX
    Explanations

    {

    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
    EndProject
    -0.79
     ***!
    -0.78
    OwnProperty
    -0.74
    出版年
    -0.72
    AddTagHelper
    -0.71
    MessageTagHelper
    -0.71
     autorytatywna
    -0.70
     ModelExpression
    -0.70
    TestingModule
    -0.69
    GraphicsUnit
    -0.69
    POSITIVE LOGITS
    ules
    0.53
     post
    0.50
     tip
    0.47
     pós
    0.45
     name
    0.44
    ptes
    0.44
     series
    0.43
     bla
    0.43
    orus
    0.42
    Toma
    0.41
    Activations Density 1.809%

    No Known Activations