© 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. 12797
    Prev
    Next
    INDEX
    Explanations

    references to aesthetic qualities or visual style

    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
     Halley
    -0.64
     purpoſe
    -0.63
    actionMode
    -0.59
    ayak
    -0.59
    setTransform
    -0.58
     Bioaccumulative
    -0.58
     diſt
    -0.57
    kháu
    -0.57
     Bols
    -0.57
     voraus
    -0.57
    POSITIVE LOGITS
     aesthetic
    3.22
     aesthetics
    2.84
     Aesthetic
    2.73
    Aesthetic
    2.58
    aesthetic
    2.56
     estética
    2.28
     Aesthetics
    2.28
     aesthetically
    2.05
     esthétique
    1.88
     estético
    1.83
    Activations Density 0.002%

    No Known Activations