© 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. 15698
    Prev
    Next
    INDEX
    Explanations

    hierarchical structures and organization pertaining to positions or arrangements

    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
    chowy
    -0.46
     tratto
    -0.40
    ेर
    -0.40
    ytte
    -0.39
    yafet
    -0.39
     
    -0.38
    раздо
    -0.38
     conciencia
    -0.38
     I
    -0.38
     incendios
    -0.37
    POSITIVE LOGITS
    PreferredItem
    0.99
     ComVisible
    0.76
    endphp
    0.75
    StructEnd
    0.75
    DoubleQuotes
    0.73
     Мексичка
    0.73
    RTLD
    0.71
     Volga
    0.71
    endpush
    0.70
     ویکی‌پدیای
    0.70
    Activations Density 0.019%

    No Known Activations