© 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. 8811
    Prev
    Next
    INDEX
    Explanations

    scientific and medical texts

    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
    makeConstraints
    -0.55
     AssemblyCompany
    -0.48
    ism
    -0.48
    urnia
    -0.48
     crystall
    -0.48
     pitié
    -0.48
    Eup
    -0.47
     enfans
    -0.46
     épaules
    -0.45
     Huerta
    -0.45
    POSITIVE LOGITS
    //
    0.73
     ddelweddau
    0.67
     utafitiHapana
    0.65
    脚注の使い方
    0.63
    ReusableCell
    0.60
     مشين
    0.60
    帖最后由
    0.60
    ábado
    0.59
    getResultList
    0.57
    ardians
    0.57
    Activations Density 0.015%

    No Known Activations