© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20345
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structural elements within technical documents, particularly related to equations, algorithms, or programming code

    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
    Negative Logits
    +#+
    -0.71
    Personensuche
    -0.66
    вгений
    -0.64
    Tikang
    -0.63
     otomatig
    -0.63
     typelib
    -0.63
    Referencie
    -0.63
    dresser
    -0.60
     disambiguazione
    -0.59
     bezeichneter
    -0.59
    POSITIVE LOGITS
    <eos>
    0.50
    CodedInputStream
    0.49
    richTextPanel
    0.47
    RunWith
    0.46
    tri
    0.46
     Gris
    0.45
    вига
    0.44
    ss
    0.44
    ViewImports
    0.43
    matur
    0.43
    Activations Density 0.343%

    No Known Activations