© 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. 15085
    Prev
    Next
    INDEX
    Explanations

    numerical constants related to decimal and floating-point values

    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
    Figures
    -0.78
    Figs
    -0.73
     Figures
    -0.68
    Tables
    -0.60
     EconPapers
    -0.60
     GRAM
    -0.58
     Figs
    -0.57
    GRAM
    -0.56
     lượt
    -0.55
    DOCTYPE
    -0.54
    POSITIVE LOGITS
     decimal
    2.00
     Decimal
    1.17
    decimal
    1.15
     decimals
    0.95
    Decimal
    0.94
    aarrggbb
    0.71
    featureID
    0.69
    InputBorder
    0.69
    CreateModel
    0.68
    mstyle
    0.65
    Activations Density 0.001%

    No Known Activations