© 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. 0-RES-MATRYOSHKA-DC
    7. 15072
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of electric light source

    oai_token-act-pair · gpt-4.1-nano
    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
    RegistryLite
    -0.78
     setuptools
    -0.71
    -------------</
    -0.64
    RuleContext
    -0.63
     PARSER
    -0.62
     怎样
    -0.61
     lighting
    -0.60
    lighting
    -0.60
     Lighting
    -0.58
    ollectionView
    -0.55
    POSITIVE LOGITS
     lamp
    2.66
     lamps
    2.45
     Lamp
    2.09
    lamp
    2.05
     Lamps
    1.96
    Lamp
    1.88
    lamps
    1.63
     LAMP
    1.47
     lampe
    1.29
    LAMP
    1.23
    Activations Density 0.003%

    No Known Activations