© 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. 12-RES-MATRYOSHKA-DC
    7. 15295
    Prev
    Next
    INDEX
    Explanations

    references to Shia Islam and its related terms

    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
     Haller
    -0.94
     ***!
    -0.92
     TableColumn
    -0.88
    couvrez
    -0.85
    uarts
    -0.82
    etheless
    -0.82
    checklist
    -0.82
     africains
    -0.81
    PerformLayout
    -0.81
     Paused
    -0.81
    POSITIVE LOGITS
     Shi
    1.57
     shi
    1.40
    Shi
    1.38
    shi
    1.10
     Shia
    1.05
     Shields
    0.93
     Shire
    0.90
    й
    0.89
    ly
    0.81
     Shih
    0.81
    Activations Density 0.007%

    No Known Activations