© 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. 14216
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols

    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
    $).
    -0.93
    enoord
    -0.78
     AssemblyCulture
    -0.69
    }$)
    -0.69
    XDECREF
    -0.64
     landing
    -0.62
    odorant
    -0.60
    Datuak
    -0.59
     ſind
    -0.59
    
    -0.59
    POSITIVE LOGITS
    $)
    1.41
     resourceCulture
    0.81
    Personensuche
    0.70
     ModelExpression
    0.68
    IsMutable
    0.56
    AddTagHelper
    0.56
    IUrlHelper
    0.56
    Архівовано
    0.55
     Мексичка
    0.54
    sizeCache
    0.54
    Activations Density 0.004%

    No Known Activations