© 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. 30671
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "file"

    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
     مشين
    -0.88
    fjspx
    -0.83
    fromnode
    -0.73
     ControllerBase
    -0.66
    تقاوى
    -0.65
     utafitiHapana
    -0.64
    foundland
    -0.63
     moro
    -0.63
    MigrationBuilder
    -0.63
     FRP
    -0.62
    POSITIVE LOGITS
    matchCondition
    0.54
    gnore
    0.52
    <eos>
    0.47
     present
    0.46
     chúng
    0.46
    imon
    0.46
     van
    0.44
     pretend
    0.43
    zyden
    0.43
    nemer
    0.43
    Activations Density 0.003%

    No Known Activations