© 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. 6622
    Prev
    Next
    INDEX
    Explanations

    references to sacred, holy, or saintly objects or persons

    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
    ()]);
    -0.79
    )");
    -0.77
    HasAnnotation
    -0.74
    --)
    -0.70
    WithIOException
    -0.70
     CHURCH
    -0.69
     Church
    -0.69
    )');
    -0.68
    HomeAsUpEnabled
    -0.68
    schild
    -0.67
    POSITIVE LOGITS
     holy
    3.09
     Holy
    2.75
     HOLY
    2.61
    Holy
    2.59
    holy
    2.59
    HOLY
    2.31
     heilige
    1.70
     Heilige
    1.45
     holiness
    1.43
     sainte
    1.40
    Activations Density 0.036%

    No Known Activations