© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91025
    Prev
    Next
    INDEX
    Explanations

    sports

    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
    Negative Logits
    TagMode
    -0.79
     متعلقه
    -0.73
    はじめに
    -0.69
     betweenstory
    -0.66
    RegressionTest
    -0.65
     CreateTagHelper
    -0.65
    IContainer
    -0.63
    Expedia
    -0.61
    MeasureSpec
    -0.61
    LookAnd
    -0.60
    POSITIVE LOGITS
     Buckley
    0.49
     veik
    0.49
     palvel
    0.48
     crystall
    0.47
    NgModule
    0.46
     buffered
    0.45
    Boli
    0.43
     fascic
    0.43
     tutkim
    0.42
    ()(
    0.42
    Activations Density 0.001%

    No Known Activations