© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 312
    Prev
    Next
    INDEX
    Explanations

    numerical data related to medical conditions or health statistics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    TagMode
    -0.59
    PRNewswire
    -0.59
     resourceCulture
    -0.52
    httphttps
    -0.52
    الدراسه
    -0.50
    cyd
    -0.49
    NameInMap
    -0.49
     gọn
    -0.48
     يتيمه
    -0.46
    Cyfarwyddwr
    -0.45
    POSITIVE LOGITS
     etc
    0.50
     finally
    0.50
     lastly
    0.50
     enfin
    0.49
     finalmente
    0.48
    reszcie
    0.48
    Finalmente
    0.47
     infine
    0.47
     Finally
    0.47
     allemaal
    0.47
    Activations Density 5.135%

    No Known Activations