© 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. 31282
    Prev
    Next
    INDEX
    Explanations

    terms that emphasize fundamental concepts or principles

    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
    ymce
    -0.77
    SuccessListener
    -0.73
    ing
    -0.73
    IOException
    -0.71
     Boyce
    -0.70
     fijo
    -0.69
    colt
    -0.68
    onPressed
    -0.68
     nhau
    -0.66
     Lucius
    -0.66
    POSITIVE LOGITS
    RegressionTest
    0.96
    printLine
    0.92
    NUMX
    0.80
    amentals
    0.77
     fundamentally
    0.76
    FUND
    0.76
     Fundament
    0.75
     Fundamental
    0.75
     Fundamentals
    0.73
     Himo
    0.73
    Activations Density 0.006%

    No Known Activations