© 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. 1-CLT-HP
    7. 16022
    Prev
    Next
    INDEX
    Explanations

    specialized vocabulary

    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
     behavior
    -0.57
     center
    -0.55
     organization
    -0.54
    behavior
    -0.52
     labor
    -0.52
    CENTER
    -0.51
     Всё
    -0.51
    ORGANIZATION
    -0.50
     color
    -0.50
    organization
    -0.49
    POSITIVE LOGITS
    uxxxx
    0.79
     linkovi
    0.74
     pinulongan
    0.72
    afficheront
    0.71
    Autoritní
    0.71
    GEBURTSDATUM
    0.64
    findpost
    0.64
    StoryboardSegue
    0.63
    はじめに
    0.62
    expandindo
    0.61
    Activations Density 0.014%

    No Known Activations