© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    terms related to the Boost C++ libraries and their functionality

    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
     Anam
    -0.84
    aryen
    -0.76
     Fara
    -0.74
    पया
    -0.73
     Arden
    -0.71
    jerry
    -0.71
     Fontana
    -0.70
     Parag
    -0.69
     Franke
    -0.69
     Watertown
    -0.69
    POSITIVE LOGITS
     BOOST
    1.56
    BOOST
    1.43
     Boost
    1.39
     boost
    1.27
    boost
    1.26
    Boost
    1.17
     boosts
    1.04
     boosting
    0.93
    oost
    0.92
     boosters
    0.92
    Activations Density 0.017%

    No Known Activations