© 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. 28066
    Prev
    Next
    INDEX
    Explanations

    structured data formats and symbols, particularly in mathematical or programming 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
    Negative Logits
     AssemblyTitle
    -0.74
    InjectAttribute
    -0.71
    ValueStyle
    -0.71
     transfieras
    -0.71
     مشين
    -0.69
    UnitTesting
    -0.69
    saraba
    -0.68
     ModelExpression
    -0.66
     nahilalakip
    -0.66
     resourceCulture
    -0.66
    POSITIVE LOGITS
     extranjero
    0.52
    hangi
    0.52
     potest
    0.50
    polazione
    0.49
    Numerology
    0.46
    pys
    0.45
     étranger
    0.45
     tibi
    0.45
     experienced
    0.44
     vider
    0.44
    Activations Density 0.165%

    No Known Activations