© 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. 0-RES-MATRYOSHKA-DC
    7. 11181
    Prev
    Next
    INDEX
    Explanations

    references to the winter season or winter-related phenomena

    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
     spring
    -1.11
     holiday
    -1.02
    #+#
    -0.89
    MessageTagHelper
    -0.88
     holidays
    -0.85
    holiday
    -0.83
     Christmas
    -0.82
     christmas
    -0.80
     springs
    -0.78
     vacation
    -0.78
    POSITIVE LOGITS
     Winter
    2.59
    Winter
    2.38
     WINTER
    1.79
    WINTER
    1.70
    winter
    1.41
     Winters
    1.24
     winter
    1.14
     winters
    0.86
     冬
    0.85
    冬
    0.82
    Activations Density 0.005%

    No Known Activations