© 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. 17334
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to liability and usage of goods or services

    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
     San
    -0.56
    <eos>
    -0.53
    rande
    -0.47
    /~
    -0.44
     [
    -0.44
     san
    -0.43
     George
    -0.43
    DropTable
    -0.42
     ↑
    -0.42
     rak
    -0.42
    POSITIVE LOGITS
     ModelExpression
    1.02
     purpoſe
    0.97
    GEBURTSDATUM
    0.97
    tagHelperRunner
    0.96
     pleaſure
    0.94
     propOrder
    0.94
     resourceCulture
    0.94
     NSCoder
    0.93
     kasarigan
    0.92
     Anſ
    0.91
    Activations Density 0.001%

    No Known Activations