© 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. 2-RES-MATRYOSHKA-DC
    7. 5945
    Prev
    Next
    INDEX
    Explanations

    mathematical statements or assertions that satisfy specific formal conditions

    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
     Greeley
    -0.62
    fill
    -0.59
     fill
    -0.59
    LabelTagHelper
    -0.58
    Filling
    -0.58
     Compliance
    -0.56
     Violations
    -0.55
     Grenville
    -0.55
     achie
    -0.54
    Compliance
    -0.54
    POSITIVE LOGITS
     satisfies
    1.68
     satisfy
    1.65
     satisfying
    1.37
     Satis
    1.35
    satis
    1.32
     satisfied
    1.17
    Satis
    1.17
    satisfies
    1.13
     satisfait
    1.08
     satisfaction
    1.06
    Activations Density 0.020%

    No Known Activations