© 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. 26755
    Prev
    Next
    INDEX
    Explanations

    terms related to regularity and regularization in mathematical contexts

    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
    wpi
    -1.04
    Personensuche
    -0.95
    VIAF
    -0.92
    complexContent
    -0.89
    ConstraintMaker
    -0.88
    endpush
    -0.86
    Portale
    -0.85
    PMailer
    -0.85
    awtextra
    -0.84
    ]--;
    -0.84
    POSITIVE LOGITS
    REGULAR
    0.63
     fille
    0.62
     pen
    0.59
     [
    0.58
    ഠ
    0.58
    strual
    0.57
     regulares
    0.57
    ed
    0.56
    pen
    0.56
     Bag
    0.55
    Activations Density 0.003%

    No Known Activations