© 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. 16258
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
    İstinadlar
    -0.52
    serif
    -0.49
     Drops
    -0.48
    eeq
    -0.47
     defy
    -0.47
    "@
    -0.47
     Drop
    -0.46
     ilmo
    -0.45
    versiti
    -0.45
     Fax
    -0.45
    POSITIVE LOGITS
     utafitiHapana
    0.69
    tagHelperRunner
    0.67
    QMetaType
    0.63
    цездатний
    0.58
     ***!
    0.57
    ⓧ
    0.57
    ModelSerializer
    0.56
     kasarigan
    0.56
     الرياضيه
    0.54
     ujednoznacz
    0.54
    Activations Density 0.098%

    No Known Activations