© 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. 3691
    Prev
    Next
    INDEX
    Explanations

    references to medical imaging markers or features in scientific or clinical documents

    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
     men
    -2.00
    Men
    -1.76
     Men
    -1.73
    men
    -1.55
     MEN
    -1.52
    MEN
    -1.51
     women
    -1.31
    women
    -1.17
    Women
    -1.10
     WOMEN
    -1.10
    POSITIVE LOGITS
     male
    1.58
     Male
    1.48
    Male
    1.47
    male
    1.44
     Man
    1.30
     MALE
    1.27
     man
    1.26
    Man
    1.20
     MAN
    1.17
    MALE
    1.09
    Activations Density 0.079%

    No Known Activations