© 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. 91077
    Prev
    Next
    INDEX
    Explanations

    biology, medicine, science

    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
    (!__
    -0.61
     StatelessWidget
    -0.56
    étique
    -0.56
    iau
    -0.55
     heats
    -0.55
     mû
    -0.54
     giới
    -0.54
    TagHelpers
    -0.53
    elsen
    -0.52
    ReusableCell
    -0.52
    POSITIVE LOGITS
     partnerships
    0.65
     linkages
    0.58
     gainera
    0.55
    تقاوى
    0.54
     connections
    0.54
    WriteTagHelper
    0.52
     дописавши
    0.51
    Дереккөздер
    0.51
    InSection
    0.51
     HasFactory
    0.49
    Activations Density 0.003%

    No Known Activations