© 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-CLT-HP
    7. 41213
    Prev
    Next
    INDEX
    Explanations

    ards/ard

    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
    ards
    -2.03
    ARD
    -1.92
    ard
    -1.84
    ARDS
    -1.48
     yard
    -1.45
    arda
    -1.40
     yards
    -1.33
    ardy
    -1.27
    ardi
    -1.27
    yard
    -1.24
    POSITIVE LOGITS
     архивлан
    0.56
    AddTagHelper
    0.52
    Jereo
    0.49
     createdBy
    0.45
    createCanvas
    0.45
    CodedInputStream
    0.44
    icals
    0.43
    fjspx
    0.43
    aking
    0.42
     intptr
    0.42
    Activations Density 1.552%

    No Known Activations