© 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. 6-RES-MATRYOSHKA-DC
    7. 409
    Prev
    Next
    INDEX
    Explanations

    terminology related to healthcare and medical institutions

    oai_token-act-pair · gemini-2.0-flash
    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
    躇
    -0.72
    andExpect
    -0.66
    oplayer
    -0.63
     divorced
    -0.61
    yarnpkg
    -0.61
    RTEE
    -0.61
    Izvori
    -0.59
     divorce
    -0.57
     energi
    -0.57
    DeleteCommand
    -0.56
    POSITIVE LOGITS
     hospital
    1.38
     hospitals
    1.27
     medical
    1.25
     healthcare
    1.23
     Hospital
    1.20
     physicians
    1.14
     physician
    1.13
     doctors
    1.11
     medicine
    1.09
     Healthcare
    1.09
    Activations Density 3.551%

    No Known Activations