© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5941
    Prev
    Next
    INDEX
    Explanations

    references to the condition diabetes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.76
     resourceCulture
    -0.73
    AddTagHelper
    -0.69
     CreateTagHelper
    -0.65
    存于互联网档案馆
    -0.64
    ▼
    -0.63
    ResponseWriter
    -0.61
    jgl
    -0.60
     Roskov
    -0.60
    modelBuilder
    -0.59
    POSITIVE LOGITS
     diabetes
    2.08
     Diabetes
    1.95
    Diabetes
    1.79
    diabetes
    1.73
     asthma
    1.22
     arthritis
    1.21
     diabetic
    1.16
     osteoporosis
    1.16
     diabetics
    1.13
     Arthritis
    1.12
    Activations Density 0.039%

    No Known Activations