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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20156
    Prev
    Next
    INDEX
    Explanations

    terms related to exposure to hazardous substances or pollutants

    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
     reveal
    -0.57
    TestRunner
    -0.57
    yos
    -0.57
     revealing
    -0.56
     revealed
    -0.55
    veness
    -0.54
    ficial
    -0.54
    y
    -0.54
     uncovered
    -0.53
     exposed
    -0.52
    POSITIVE LOGITS
    Vidite
    0.86
     fidé
    0.68
     ainfi
    0.65
     historiques
    0.63
     EconPapers
    0.63
     fraî
    0.61
     rembour
    0.61
     hjemme
    0.61
    JAMIN
    0.61
     réguli
    0.60
    Activations Density 0.003%

    No Known Activations