© 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. 4230
    Prev
    Next
    INDEX
    Explanations

    references to Jewish people and related topics, especially terms associated with Jewish identity, history, and persecution

    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
     Monfieur
    -0.74
    LookAnd
    -0.72
     Galen
    -0.72
     Thun
    -0.71
    -------------</
    -0.68
     Burrell
    -0.68
     subsoil
    -0.67
     Sermons
    -0.67
     Sixteenth
    -0.66
     ویکی‌پدی
    -0.66
    POSITIVE LOGITS
     Jews
    2.98
     Jewish
    2.72
    Jewish
    2.44
    Jews
    2.38
     Jew
    2.20
     jewish
    2.05
    jewish
    1.98
     judíos
    1.86
    Jew
    1.79
     jüdis
    1.73
    Activations Density 0.009%

    No Known Activations