© 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. 6199
    Prev
    Next
    INDEX
    Explanations

    scientific processes

    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
    queryInterface
    -0.63
    Hentet
    -0.57
     inderdaad
    -0.55
     quelquefois
    -0.53
     архивлан
    -0.52
    sizeCache
    -0.51
     бывает
    -0.51
    WebVitals
    -0.48
    AsUp
    -0.48
     bornes
    -0.48
    POSITIVE LOGITS
    TagHelpers
    0.59
    __*/
    0.57
    paksa
    0.55
     autorytatywna
    0.54
     couldn
    0.52
    instead
    0.51
    ServiceModel
    0.50
     Instead
    0.49
    Instead
    0.49
    ERTY
    0.48
    Activations Density 0.211%

    No Known Activations