© 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. 25858
    Prev
    Next
    INDEX
    Explanations

    responses and categories related to quiz or survey answers

    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
     raw
    -0.47
    fflush
    -0.46
    laget
    -0.46
    bó
    -0.44
    /');
    -0.43
     both
    -0.42
     Fried
    -0.41
    ตน
    -0.41
     band
    -0.41
     raise
    -0.41
    POSITIVE LOGITS
    存于互联网档案馆
    0.82
    tagHelperRunner
    0.79
    ArrowToggle
    0.77
    sizeCache
    0.71
    NameInMap
    0.69
     aDecoder
    0.69
     متعلقه
    0.68
     Италијани
    0.68
     jspb
    0.67
    lgari
    0.66
    Activations Density 0.084%

    No Known Activations