© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and references to publications or citations

    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
     المعيارى
    -0.59
     Мексичка
    -0.57
     tarko
    -0.56
    исленность
    -0.56
    JspWriter
    -0.56
    enterOuterAlt
    -0.55
    šanās
    -0.55
     tempio
    -0.55
    بوابة
    -0.54
    TagMode
    -0.54
    POSITIVE LOGITS
    ↵↵↵
    0.64
    unhofer
    0.61
    ↵↵
    0.60
    ↵
    0.59
    <eos>
    0.56
     estre
    0.54
    henswürdigkeiten
    0.52
    cassert
    0.50
    ↵↵↵↵
    0.50
    তথ্যসূত্র
    0.48
    Activations Density 0.034%

    No Known Activations