© 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. 20939
    Prev
    Next
    INDEX
    Explanations

    instances of legal arguments and assertions

    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
     Live
    -0.45
    Filed
    -0.42
     Ed
    -0.39
     et
    -0.38
     ==
    -0.37
    govine
    -0.37
    Live
    -0.37
    /
    -0.37
     D
    -0.36
     phản
    -0.36
    POSITIVE LOGITS
     ModelExpression
    0.92
    ValueStyle
    0.87
    Бахар
    0.85
     defaultstate
    0.82
    ImageContext
    0.78
     مرئيه
    0.74
    providedIn
    0.73
     linkovi
    0.71
     الحره
    0.71
    NgModule
    0.70
    Activations Density 0.054%

    No Known Activations