© 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. 23778
    Prev
    Next
    INDEX
    Explanations

    mentions of Islam and Islamic concepts

    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
    ########.
    -0.78
    setVerticalGroup
    -0.76
    )");
    -0.75
    ----+
    -0.71
    UnusedPrivate
    -0.70
    )”.
    -0.69
    __':
    -0.69
    ViewFeatures
    -0.68
     Untold
    -0.68
     }}$}
    -0.67
    POSITIVE LOGITS
     Islam
    1.18
    Islam
    1.02
     islam
    0.88
    islam
    0.86
     Islamic
    0.82
     ISLAM
    0.81
     Osm
    0.72
    Islamic
    0.70
     الإسلامية
    0.70
     الإسلام
    0.69
    Activations Density 0.003%

    No Known Activations