© 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
    2. Gemma-2-2B
    3. 1-RES-MATRYOSHKA-DC
    4. 785
    Prev
    Next
    INDEX
    Explanations

    references to the Jewish people and Israel

    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
    Pato
    -0.62
     externi
    -0.60
    יצוני
    -0.59
     lomb
    -0.57
     Sart
    -0.56
    kirch
    -0.56
     Kalk
    -0.55
     surla
    -0.54
     Kirch
    -0.53
    vnd
    -0.53
    POSITIVE LOGITS
     Israel
    3.09
    Israel
    2.84
     Israeli
    2.78
    Israeli
    2.55
     Israël
    2.53
     Israelis
    2.52
     ISRAEL
    2.50
     israel
    2.44
     Jewish
    2.30
     Jews
    2.19
    Activations Density 0.788%

    No Known Activations