© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1534
    Prev
    Next
    INDEX
    Explanations

    references to divine attributes, specifically references to God and theological statements about God's nature and actions

    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
    Negative Logits
     houſe
    -0.84
     Houſe
    -0.71
     myſelf
    -0.66
     ſee
    -0.64
     leſs
    -0.59
     समीक्षाएं
    -0.59
     Theſe
    -0.58
     itſelf
    -0.57
     tuy
    -0.57
     pleaſure
    -0.57
    POSITIVE LOGITS
     God
    4.63
    God
    4.22
     god
    3.95
     GOD
    3.56
    god
    3.50
    GOD
    3.22
     Gods
    2.75
     Dios
    2.56
     Dieu
    2.48
     gods
    2.47
    Activations Density 0.214%

    No Known Activations