© 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. 30829
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "at" in various contexts

    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
    oredCriteria
    -0.75
    Navig
    -0.59
     кіль
    -0.57
    AccessFile
    -0.57
     Navig
    -0.57
    Jeografia
    -0.55
     definitivo
    -0.54
     vägen
    -0.54
     raiſ
    -0.52
    RenderAtEndOf
    -0.52
    POSITIVE LOGITS
    uesia
    0.62
    serviceWorker
    0.60
     Vitae
    0.55
     Eles
    0.53
    Tembelea
    0.52
    __*/
    0.52
    Els
    0.50
    AccessorTable
    0.50
     /\.(
    0.50
    èdia
    0.49
    Activations Density 0.000%

    No Known Activations