© 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. 9897
    Prev
    Next
    INDEX
    Explanations

    food items and dishes typically associated with a cuisine or dining experience

    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
    Not in Any Lists

    No Comments

    Negative Logits
     gainera
    -0.47
    Ros
    -0.47
    isle
    -0.46
    (/^
    -0.46
    かけ
    -0.45
    掛け
    -0.45
     trailed
    -0.44
     Spri
    -0.44
     mix
    -0.43
     sprinkle
    -0.43
    POSITIVE LOGITS
     <=",
    0.89
     >=",
    0.83
    sizeCache
    0.82
     Roskov
    0.81
    EndInit
    0.80
    tvguidetime
    0.79
    thâu
    0.79
     kasarigan
    0.77
    awtextra
    0.76
     bambou
    0.75
    Activations Density 0.028%

    No Known Activations