© 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. 6-RES-MATRYOSHKA-DC
    7. 1208
    Prev
    Next
    INDEX
    Explanations

    the word "default" in code and configuration files

    oai_token-act-pair · gemini-2.0-flash
    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
    expandindo
    -0.83
     Viber
    -0.80
     
    -0.79
     TabLayout
    -0.77
     cdti
    -0.77
    SourceChecksum
    -0.75
     postIndex
    -0.74
    اریخ
    -0.73
    AccessFile
    -0.73
    {}",
    -0.73
    POSITIVE LOGITS
    default
    1.77
     Default
    1.75
    Default
    1.73
     default
    1.70
     defaults
    1.60
     DEFAULT
    1.55
    DEFAULT
    1.49
     Defaults
    1.40
    defaults
    1.36
     defaulted
    1.34
    Activations Density 0.087%

    No Known Activations