© 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. 32237
    Prev
    Next
    INDEX
    Explanations

    references to mathematical notation, specifically involving brackets and similar symbols

    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
    ven
    -0.56
    וך
    -0.56
    tafogo
    -0.56
    ].(
    -0.56
    الحياه
    -0.55
    TintMode
    -0.55
    ทย
    -0.54
    Зноскі
    -0.54
    λλην
    -0.54
    multer
    -0.53
    POSITIVE LOGITS
     للاسماء
    0.91
     Beecher
    0.72
    InSection
    0.66
     Scherer
    0.66
     maat
    0.64
    μά
    0.62
     âmes
    0.62
    mapTo
    0.62
     муніципалі
    0.61
     berätt
    0.61
    Activations Density 0.033%

    No Known Activations