© 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. 24916
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to contractual obligations

    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
     Estudiantes
    -0.47
    Karten
    -0.45
    AddField
    -0.44
     Karte
    -0.44
    Maps
    -0.43
    IVersion
    -0.43
    Geograf
    -0.42
    IntentFilter
    -0.42
     clearfix
    -0.42
     Maps
    -0.41
    POSITIVE LOGITS
     procurement
    0.88
     Procurement
    0.87
     bidders
    0.85
    Rhestr
    0.73
     bidder
    0.73
    Procurement
    0.72
     NUKAT
    0.71
     bidding
    0.71
     vendors
    0.69
     contracts
    0.68
    Activations Density 0.016%

    No Known Activations