© 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. 3-RES-MATRYOSHKA-DC
    7. 140
    Prev
    Next
    INDEX
    Explanations

    mentions of a male person as "he" or with "him" possessive pronouns.

    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
     We
    -1.80
     we
    -1.79
    We
    -1.77
    we
    -1.66
     ourselves
    -1.48
     our
    -1.45
    Our
    -1.39
     Our
    -1.35
    我们
    -1.30
     我们
    -1.27
    POSITIVE LOGITS
     him
    1.76
     himself
    1.68
    himself
    1.52
     his
    1.38
     he
    1.31
     Himself
    1.31
    him
    1.25
     herself
    1.20
     she
    1.19
     HIM
    1.17
    Activations Density 0.835%

    No Known Activations