© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13747
    Prev
    Next
    INDEX
    Explanations

    visual features related to painted patterns or surfaces

    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
     painting
    -1.20
     paintings
    -1.17
     Painting
    -1.01
    painting
    -0.95
     Paintings
    -0.86
     painter
    -0.85
     PAINTING
    -0.85
     painters
    -0.84
    Painting
    -0.77
     dipinto
    -0.69
    POSITIVE LOGITS
     Paint
    1.73
     paint
    1.70
    Paint
    1.62
    paint
    1.21
     Paints
    0.88
     PAINT
    0.80
     paints
    0.72
    Hozzáférés
    0.67
    toThrow
    0.65
     färg
    0.60
    Activations Density 0.001%

    No Known Activations