© 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. 32275
    Prev
    Next
    INDEX
    Explanations

    quantitative relationships and correlations between variables in scientific data

    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
     an
    -0.52
     statistically
    -0.50
     significantly
    -0.44
    entlicher
    -0.44
     κό
    -0.44
     Unters
    -0.43
     statistical
    -0.43
    лер
    -0.42
     Mund
    -0.42
     gender
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.76
    BeginContext
    0.75
    makeConstraints
    0.75
     <=",
    0.75
     HasFactory
    0.75
     ModelExpression
    0.75
    المناصب
    0.75
    χρι
    0.73
     stället
    0.72
     CGSize
    0.69
    Activations Density 0.074%

    No Known Activations