© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16253
    Prev
    Next
    INDEX
    Explanations

    references to places, particularly community-focused establishments such as post offices, public houses, and historic sites

    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
    LayoutPanel
    -0.61
    TintMode
    -0.60
     seating
    -0.59
    — 
    -0.57
    بوابة
    -0.56
    loten
    -0.56
    – 
    -0.54
    WebElementEntity
    -0.54
     Италијани
    -0.53
    Спољашње
    -0.52
    POSITIVE LOGITS
     gendar
    0.73
     squire
    0.69
     antelope
    0.62
     Charlemagne
    0.60
     antlers
    0.60
     Theſe
    0.60
     dieß
    0.59
     QuickBooks
    0.58
     anthropologists
    0.58
     linguistics
    0.57
    Activations Density 0.064%

    No Known Activations