© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16537
    Prev
    Next
    INDEX
    Explanations

    food group classifications and their diversity in dietary studies

    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
     المعيارى
    -0.94
    Tikang
    -0.74
     lenker
    -0.72
    RenderAtEndOf
    -0.71
    ConstraintMaker
    -0.69
     виправивши
    -0.64
    transQ
    -0.63
    adecimal
    -0.62
    batore
    -0.62
     referenties
    -0.62
    POSITIVE LOGITS
    apimachinery
    0.47
    httphttps
    0.47
    existsSync
    0.46
    ,
    0.46
     временем
    0.46
    показания
    0.46
     paździer
    0.45
     &
    0.44
    arei
    0.44
    =
    0.43
    Activations Density 0.055%

    No Known Activations