© 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. 9154
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance improvements and efficiency gains in processes or systems

    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
     ketat
    -0.54
    κι
    -0.53
    Payer
    -0.50
     niyang
    -0.50
     gerichtet
    -0.49
     Manley
    -0.46
    pendenti
    -0.45
    Parsing
    -0.44
     Himo
    -0.44
     esternos
    -0.43
    POSITIVE LOGITS
     improvements
    0.93
     improved
    0.88
     improvement
    0.87
     enhancements
    0.85
    improved
    0.84
     improve
    0.84
    improve
    0.82
    Improvements
    0.78
     Improvement
    0.77
     Improved
    0.77
    Activations Density 0.621%

    No Known Activations