© 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. 2833
    Prev
    Next
    INDEX
    Explanations

    references to steady states in physical systems

    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
     الفلك
    -0.67
     Cách
    -0.65
    verständlich
    -0.63
     Albion
    -0.60
    Décès
    -0.60
     Dunes
    -0.60
    ủng
    -0.59
     Wikimedijinoj
    -0.58
     leeftijd
    -0.57
    orological
    -0.57
    POSITIVE LOGITS
     steady
    3.25
     Steady
    3.08
    Steady
    2.95
    steady
    2.92
     steadily
    1.76
     stea
    1.74
    teady
    1.65
     stead
    1.42
     Stead
    1.20
    稳
    1.13
    Activations Density 0.014%

    No Known Activations