© 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. 46
    Prev
    Next
    INDEX
    Explanations

    references to a specific male individual or pronouns related to him

    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
     uſe
    -0.82
    seamnă
    -0.81
     purpoſe
    -0.79
     preſent
    -0.79
     Efq
    -0.79
     ſmall
    -0.77
     anſ
    -0.74
     pleaſure
    -0.73
     faſt
    -0.72
    ſelves
    -0.72
    POSITIVE LOGITS
     he
    3.73
     she
    3.09
     He
    3.06
    He
    2.98
     him
    2.48
     his
    2.44
    she
    2.42
    She
    2.41
     She
    2.28
     himself
    2.14
    Activations Density 2.742%

    No Known Activations