© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3187
    Prev
    Next
    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.60
    TagMode
    -0.51
     StatefulWidget
    -0.49
    kháu
    -0.49
    InputTagHelper
    -0.49
    AddTagHelper
    -0.48
    Rhestr
    -0.47
    MessageTagHelper
    -0.47
    
    -0.46
    umenter
    -0.45
    POSITIVE LOGITS
     متحده
    0.57
    estacks
    0.56
    enumi
    0.56
     noqa
    0.55
    DrawerLayout
    0.54
     lady
    0.53
    preuve
    0.52
    :+:
    0.52
     Berta
    0.52
     kiệm
    0.51
    Activations Density 0.006%

    No Known Activations