© 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. 5995
    Prev
    Next
    INDEX
    Explanations

    terms related to directionality and directed graphs

    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
    ikkert
    -0.77
     Jank
    -0.75
     Hab
    -0.75
    flakes
    -0.75
    <h6>
    -0.74
     Watanabe
    -0.74
    ngdoc
    -0.73
    letus
    -0.71
    antMatchers
    -0.70
     hab
    -0.70
    POSITIVE LOGITS
     directions
    1.28
     directors
    1.18
     directing
    1.15
     direction
    1.12
     Directors
    1.12
     Direction
    1.11
     Directions
    1.10
    directions
    1.09
     Dir
    1.03
     DIRECTION
    1.03
    Activations Density 0.129%

    No Known Activations