© 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. 1-CLT-HP
    7. 10117
    Prev
    Next
    INDEX
    Explanations

    wheat

    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
     Wheat
    -0.93
    Wheat
    -0.81
     wheat
    -0.79
    wheat
    -0.61
     pleaſure
    -0.53
     Inſ
    -0.51
     Houſe
    -0.51
    contentLoaded
    -0.51
    
    -0.50
     Whales
    -0.50
    POSITIVE LOGITS
     المعيارى
    0.73
     autorytatywna
    0.60
    __(/*!
    0.60
    FunctionFlags
    0.56
    CodeAttribute
    0.56
    omány
    0.54
    SizeF
    0.51
     iconTwitter
    0.50
     الرياضيه
    0.50
    MessageTagHelper
    0.49
    Activations Density 0.025%

    No Known Activations