© 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. 9165
    Prev
    Next
    INDEX
    Explanations

    specific dates and time references in text

    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
    <eos>
    -0.52
     
    -0.52
      
    -0.50
    くれました
    -0.50
    tinyos
    -0.49
     {
    -0.47
    ↵↵
    -0.47
     until
    -0.46
    ision
    -0.46
    newswire
    -0.46
    POSITIVE LOGITS
     nakalista
    0.92
     itſelf
    0.79
    NUMX
    0.79
    AccessorTable
    0.77
    NameInMap
    0.77
     estekak
    0.75
     للاسماء
    0.75
     ſind
    0.74
     $_"
    0.74
     ſmall
    0.73
    Activations Density 0.078%

    No Known Activations