© 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. 5966
    Prev
    Next
    INDEX
    Explanations

    health, medicine

    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
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -0.50
    ]='\
    -0.46
    FailureListener
    -0.44
     joh
    -0.41
     focused
    -0.40
     focus
    -0.40
    RegressionTest
    -0.39
    ,
    -0.38
     re
    -0.37
     empowerment
    -0.37
    POSITIVE LOGITS
     שוליים
    0.79
    TestingModule
    0.77
     CreateTagHelper
    0.73
     مرئيه
    0.69
     protoimpl
    0.69
    MLLoader
    0.69
    kloped
    0.68
     PÉ
    0.67
     مشين
    0.67
     يتيمه
    0.65
    Activations Density 0.003%

    No Known Activations