© 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. 3497
    Prev
    Next
    INDEX
    Explanations

    the presence of specific mathematical structures related to spin configurations and matrices in the scientific text

    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
     textStatus
    -0.57
     privés
    -0.50
     nyky
    -0.49
    WebpackPlugin
    -0.49
     myö
    -0.49
     BoxDecoration
    -0.49
    XMLSchema
    -0.48
    tonode
    -0.48
    multirow
    -0.47
     AssemblyTitle
    -0.46
    POSITIVE LOGITS
    rungsseite
    0.74
    autique
    0.67
    MessageTagHelper
    0.65
     Roskov
    0.65
    <?>>
    0.65
    contentLoaded
    0.63
    ]<=
    0.63
    matism
    0.62
     Wiktionnaire
    0.61
     HO
    0.60
    Activations Density 0.150%

    No Known Activations