© 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. 14044
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving curly braces and their nesting levels

    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
    annelse
    -0.59
    ktop
    -0.58
    PreExecute
    -0.55
     devi
    -0.54
    RuleContext
    -0.54
    談社
    -0.54
     Yakima
    -0.52
    Wolfe
    -0.52
     Elden
    -0.52
    त्ता
    -0.52
    POSITIVE LOGITS
    aarrggbb
    0.81
     للاسماء
    0.67
     AssemblyCulture
    0.63
     Besar
    0.60
    脚注の使い方
    0.60
    InjectAttribute
    0.59
    saraba
    0.59
     disambiguazione
    0.59
     Fros
    0.58
     häls
    0.57
    Activations Density 0.050%

    No Known Activations