© 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. 14928
    Prev
    Next
    INDEX
    Explanations

    references to transactions and contractual obligations involving buyers and sellers

    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
    RectangleBorder
    -0.81
     Theſe
    -0.76
    })();
    -0.74
     StatefulWidget
    -0.73
    AndroidJUnit
    -0.71
    NameInMap
    -0.70
    "]);
    -0.70
     "));
    -0.69
     Efq
    -0.69
    omock
    -0.69
    POSITIVE LOGITS
    cension
    0.44
    ologist
    0.44
     landlord
    0.43
    koz
    0.41
    jetunion
    0.40
    lorn
    0.40
    N
    0.40
    fed
    0.40
     ostavi
    0.40
    z
    0.40
    Activations Density 0.072%

    No Known Activations