© 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. 9142
    Prev
    Next
    INDEX
    Explanations

    instances of the word "brief" or its variations, indicating a focus on brief descriptions or summaries

    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
     Sot
    -0.62
    prilis
    -0.58
    ADELPHIA
    -0.55
    MessageTagHelper
    -0.53
     richting
    -0.52
    adamente
    -0.51
     cikin
    -0.50
     Loth
    -0.49
     Yad
    -0.49
    empel
    -0.49
    POSITIVE LOGITS
     Brief
    0.77
     brief
    0.77
     bref
    0.77
    曖昧さ回避
    0.77
    enumi
    0.73
     briefly
    0.70
    EndInit
    0.70
    IBarButtonItem
    0.70
    rmtree
    0.70
     BRIEF
    0.68
    Activations Density 0.006%

    No Known Activations