© 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. 1-RES-MATRYOSHKA-DC
    7. 1190
    Prev
    Next
    INDEX
    Explanations

    references to women and topics related to women's health and reproductive issues

    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
    -0.92
    Men
    -0.85
    men
    -0.82
     Men
    -0.81
     MEN
    -0.70
     guys
    -0.69
    MEN
    -0.67
     dad
    -0.64
     hommes
    -0.64
     man
    -0.62
    POSITIVE LOGITS
     women
    3.05
     Women
    2.89
    Women
    2.80
    women
    2.69
     WOMEN
    2.59
     woman
    2.48
     Woman
    2.36
    WOMEN
    2.30
    Woman
    2.17
     womens
    2.16
    Activations Density 0.312%

    No Known Activations