© 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. 0-CLT-HP
    7. 95645
    Prev
    Next
    INDEX
    Explanations

    fractive

    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
    ReusableCell
    -0.61
    jectures
    -0.59
     silencio
    -0.57
    äldrar
    -0.57
     silence
    -0.57
    帖最后由
    -0.57
    verb
    -0.56
    cephala
    -0.56
    Gambas
    -0.54
    athlete
    -0.54
    POSITIVE LOGITS
    ly
    0.76
     Cupid
    0.70
     MainAxisSize
    0.65
    ity
    0.63
    ness
    0.62
    expandindo
    0.57
    en
    0.57
    googleapis
    0.55
     estimés
    0.54
    usion
    0.54
    Activations Density 1.851%

    No Known Activations