© 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. 297
    Prev
    Next
    INDEX
    Explanations

    female pronouns, titles, and proper names

    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
     himself
    -0.96
     Himself
    -0.81
    ⓧ
    -0.81
    himself
    -0.73
     koji
    -0.71
     који
    -0.71
    limus
    -0.65
     boyhood
    -0.62
     Zeke
    -0.61
     Jr
    -0.59
    POSITIVE LOGITS
     herself
    1.56
    herself
    1.14
     actress
    0.94
     bint
    0.94
     she
    0.93
     feminist
    0.92
     goddess
    0.91
     actresses
    0.90
     womanhood
    0.89
     businesswoman
    0.89
    Activations Density 2.701%

    No Known Activations