© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1062
    Prev
    Next
    INDEX
    Explanations

    scientific language referring to the physical effect of exposition to some substance

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mahoney
    -0.91
     ISNI
    -0.85
     Bartol
    -0.75
     Hinton
    -0.74
     PopupWindow
    -0.73
     Ottawa
    -0.73
     Moran
    -0.71
     Dwyer
    -0.71
     TAMBÉM
    -0.70
     Miche
    -0.69
    POSITIVE LOGITS
     covers
    0.89
    Comp
    0.85
    covers
    0.85
     Mald
    0.84
     Mérimée
    0.81
     fVar
    0.81
    Covers
    0.81
    screens
    0.79
     cover
    0.78
    Cub
    0.78
    Activations Density 3.776%

    No Known Activations