© 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. 12-RES-MATRYOSHKA-DC
    7. 3173
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to religion and religious beliefs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.85
     uParam
    -0.78
    FieldBuilder
    -0.75
    '));
    -0.71
    TagHelper
    -0.69
    }`).
    -0.69
     EconPapers
    -0.68
    nowned
    -0.67
     zám
    -0.67
    ]")]
    -0.66
    POSITIVE LOGITS
     religieuse
    1.02
     relig
    0.98
     Religion
    0.95
     Religious
    0.93
     religious
    0.91
     Religions
    0.91
     religions
    0.91
     religieuses
    0.90
     religion
    0.89
     religioso
    0.89
    Activations Density 0.037%

    No Known Activations