© 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. 17736
    Prev
    Next
    INDEX
    Explanations

    sections of text containing tabular data or summary statistics

    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
    gants
    -0.52
    abetes
    -0.50
     aste
    -0.48
     dever
    -0.46
    Atta
    -0.46
    rrggbb
    -0.45
     thinking
    -0.44
    jack
    -0.43
     Pry
    -0.43
    decine
    -0.43
    POSITIVE LOGITS
    Portály
    0.78
     للاسماء
    0.70
    makeConstraints
    0.67
    CppMethod
    0.65
     <>",
    0.61
    िखित
    0.59
     tartalomajánló
    0.59
     дописавши
    0.59
    Parcelize
    0.59
    TableHead
    0.59
    Activations Density 0.008%

    No Known Activations