© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15918
    Prev
    Next
    INDEX
    Explanations

    references to sources of light or illumination, particularly sunlight, moonlight, or daylight

    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
    CopyWith
    -0.74
    gameserver
    -0.63
     CreateTagHelper
    -0.63
    beforeEach
    -0.62
    niająca
    -0.57
    enschappelijke
    -0.56
    WriteTagHelper
    -0.56
    mergeFrom
    -0.56
     Andromeda
    -0.56
     conf
    -0.55
    POSITIVE LOGITS
     sunlight
    2.80
     daylight
    2.03
     Sunlight
    2.00
    Sunlight
    1.83
     sunshine
    1.81
     Daylight
    1.80
    daylight
    1.69
    sunshine
    1.25
    Sunshine
    1.18
     Sunshine
    1.15
    Activations Density 0.003%

    No Known Activations