© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14901
    Prev
    Next
    INDEX
    Explanations

    references to divine beings or deities

    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
     alatt
    -0.41
     reikia
    -0.41
    起來
    -0.40
    aleza
    -0.40
    ot
    -0.38
    prototype
    -0.37
     minuten
    -0.37
    y
    -0.36
     Jerusalén
    -0.36
    
    -0.35
    POSITIVE LOGITS
     gods
    3.50
     Gods
    3.02
    gods
    2.83
    Gods
    2.66
     dioses
    2.11
     deities
    1.80
     dieux
    1.69
     Götter
    1.39
     goddesses
    1.24
     goddess
    1.14
    Activations Density 0.002%

    No Known Activations