© 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. 16914
    Prev
    Next
    INDEX
    Explanations

    references to breakfast dishes

    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
     esternos
    -0.84
    NUMX
    -0.83
     createSlice
    -0.80
     समीक्षाओं
    -0.75
     pym
    -0.74
    +:+
    -0.74
    obald
    -0.74
     Minaj
    -0.72
    Alike
    -0.71
    RenderAtEndOf
    -0.70
    POSITIVE LOGITS
     breakfast
    1.21
     Breakfast
    1.17
    breakfast
    1.06
    Breakfast
    1.05
     breakfasts
    1.03
     Frühstück
    0.94
     desayuno
    0.77
    早餐
    0.73
    bijt
    0.72
     Morning
    0.61
    Activations Density 0.002%

    No Known Activations