© 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. 3-RES-MATRYOSHKA-DC
    7. 1685
    Prev
    Next
    INDEX
    Explanations

    mentions of experimental design for scientific papers

    oai_token-act-pair · gemini-2.0-flash
    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
    ThroughAttribute
    -0.88
    endregion
    -0.65
    setAccessible
    -0.62
    fycat
    -0.60
    chymal
    -0.58
     Wurzel
    -0.56
    CDATA
    -0.56
    ionato
    -0.55
     XCTest
    -0.55
     eventdata
    -0.54
    POSITIVE LOGITS
     design
    3.03
     Design
    2.84
    Design
    2.81
    design
    2.72
     DESIGN
    2.72
     designs
    2.66
    DESIGN
    2.59
     designed
    2.48
     designers
    2.47
     designing
    2.45
    Activations Density 0.240%

    No Known Activations