© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92221
    Prev
    Next
    INDEX
    Explanations

    stand

    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
     stand
    -1.50
    Stand
    -1.08
    stand
    -1.01
     Stand
    -0.99
     stood
    -0.96
     STAND
    -0.85
     standing
    -0.81
     stands
    -0.72
    STAND
    -0.68
     للمعارف
    -0.61
    POSITIVE LOGITS
    s
    0.61
    sus
    0.57
    sof
    0.55
    prior
    0.55
     Gaylord
    0.55
    intur
    0.54
     orientations
    0.54
     journals
    0.53
     Octa
    0.53
    waw
    0.53
    Activations Density 0.067%

    No Known Activations