© 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. 14480
    Prev
    Next
    INDEX
    Explanations

    modules related to caching and data retrieval operations

    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
    "):
    -0.59
     fins
    -0.54
     Avril
    -0.51
     }}}{
    -0.51
    )}}{
    -0.50
    ")==
    -0.50
    )':
    -0.50
     kain
    -0.49
     dataSnapshot
    -0.49
    سیون
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.75
    sizeCache
    0.72
    TestTools
    0.72
     Roskov
    0.72
    曖昧さ回避
    0.66
    зулта
    0.63
     الدولى
    0.62
    Gemeinden
    0.61
    tableFuture
    0.60
    ContentAsync
    0.59
    Activations Density 0.005%

    No Known Activations