© 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. 20266
    Prev
    Next
    INDEX
    Explanations

    terms associated with inventions and innovations

    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
    tagHelperRunner
    -0.75
    ništvo
    -0.71
    ViewFeatures
    -0.70
    rawDesc
    -0.64
    "}},
    -0.63
     chré
    -0.62
    HtmlAttribute
    -0.61
     समीक्षाओं
    -0.61
    دانشنامهٔ
    -0.61
    //
    -0.60
    POSITIVE LOGITS
     reality
    0.53
     Arrive
    0.53
     возможно
    0.52
    Viitteet
    0.51
     T
    0.50
     fact
    0.49
    mybatisplus
    0.49
    COME
    0.49
     Then
    0.49
     Come
    0.49
    Activations Density 0.136%

    No Known Activations