© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 929
    Prev
    Next
    INDEX
    Explanations

    sections and subsections in a structured document

    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
    SharedCtor
    -0.69
    WireFormatLite
    -0.68
    RenderAtEndOf
    -0.65
    PreferredItem
    -0.63
     ModelExpression
    -0.59
     Paglinawan
    -0.58
    SharedDtor
    -0.57
    VIAF
    -0.55
    setLayoutParams
    -0.55
    Derbyniad
    -0.54
    POSITIVE LOGITS
    RelativeTo
    0.59
     Conseils
    0.57
    ynb
    0.56
    Sucesor
    0.52
     }}$}
    0.52
    RectangleBorder
    0.51
     noix
    0.49
     sube
    0.49
     Redacción
    0.49
     Ns
    0.48
    Activations Density 0.302%

    No Known Activations