© 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. 11119
    Prev
    Next
    INDEX
    Explanations

    references to historical battles, geographic locations, and religious institutions

    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
    слей
    -0.57
     part
    -0.54
    ſelf
    -0.53
     entire
    -0.52
    σθαι
    -0.52
     Scritto
    -0.51
    NAM
    -0.50
     official
    -0.49
     overall
    -0.49
     fault
    -0.49
    POSITIVE LOGITS
     للاسماء
    0.86
    KommentareTeilen
    0.78
    aarrggbb
    0.76
     >=",
    0.74
    }{*}{
    0.73
     الاطلاع
    0.73
     referenties
    0.71
    NameInMap
    0.71
     jScrollPane
    0.71
    TintMode
    0.70
    Activations Density 0.076%

    No Known Activations