© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11439
    Prev
    Next
    INDEX
    Explanations

    terms related to ethnicity and chemical compounds

    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
     Westinghouse
    -0.82
     الحره
    -0.73
     Welle
    -0.73
     Hera
    -0.72
    OpenHelper
    -0.72
     Catharine
    -0.70
     διά
    -0.70
     Geller
    -0.70
    randrange
    -0.69
    prese
    -0.68
    POSITIVE LOGITS
     eth
    1.08
     Eth
    1.00
    eth
    0.93
    Eth
    0.86
     ETH
    0.84
    setVerticalGroup
    0.76
    odils
    0.76
    ETH
    0.75
    protoc
    0.74
     BoxFit
    0.70
    Activations Density 0.006%

    No Known Activations