© 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. 20340
    Prev
    Next
    INDEX
    Explanations

    references to types of evidence in a legal or judicial context

    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
    parti
    -0.53
    wim
    -0.47
     Söz
    -0.46
    quist
    -0.45
    Donald
    -0.45
    љи
    -0.44
    loo
    -0.43
     =>
    -0.43
     '/';
    -0.43
     söz
    -0.43
    POSITIVE LOGITS
     wireType
    7.28
    AndEndTag
    1.43
    ValueStyle
    1.35
     fieldNum
    1.20
     resourceCulture
    1.11
    styleType
    1.06
     iNdEx
    1.00
    sidemargin
    0.98
    TagMode
    0.95
     postIndex
    0.94
    Activations Density 0.000%

    No Known Activations