© 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. 20-CLT-HP
    7. 71499
    Prev
    Next
    INDEX
    Explanations

    medicine and biology contexts

    np_max-act-logits · 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
    oredCriteria
    -0.73
    rungsseite
    -0.71
    ArrowToggle
    -0.62
    chartInstance
    -0.61
     InputDecoration
    -0.59
     propOrder
    -0.56
    EDM
    -0.55
    ulage
    -0.52
    bitField
    -0.52
     Antilles
    -0.52
    POSITIVE LOGITS
     Program
    0.60
     co
    0.58
     Programme
    0.57
     programmed
    0.57
     cos
    0.54
    programmed
    0.54
    Program
    0.52
    Normdaten
    0.52
     coin
    0.51
    väg
    0.51
    Activations Density 0.004%

    No Known Activations