© 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. 30682
    Prev
    Next
    INDEX
    Explanations

    discussions about religious leaders and community events

    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
    Negative Logits
     Савезне
    -0.94
     Jefus
    -0.88
     ―――――
    -0.77
    StructEnd
    -0.76
     Meksiku
    -0.75
     iſt
    -0.75
     itſelf
    -0.75
    ArrowToggle
    -0.74
    PMailer
    -0.73
     المعيارى
    -0.72
    POSITIVE LOGITS
    ch
    0.52
     imperio
    0.48
    hiva
    0.47
     vele
    0.46
    enter
    0.45
     dari
    0.45
    le
    0.43
     from
    0.43
     thought
    0.43
    Rabbi
    0.42
    Activations Density 0.020%

    No Known Activations