© 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. 26129
    Prev
    Next
    INDEX
    Explanations

    terms related to device drivers

    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
    Referensi
    -0.82
    ethane
    -0.82
    BibitemShut
    -0.75
    ethene
    -0.74
    Weblinks
    -0.72
    NOPQRST
    -0.70
    ​=
    -0.70
     BNE
    -0.68
     peindre
    -0.67
     portata
    -0.66
    POSITIVE LOGITS
    man
    0.77
     “
    0.76
     Drivers
    0.73
    driver
    0.71
     drivers
    0.69
     Driver
    0.69
    y
    0.69
     driver
    0.69
    <h4>
    0.68
     ‘
    0.65
    Activations Density 0.010%

    No Known Activations