© 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. 10165
    Prev
    Next
    INDEX
    Explanations

    GPU

    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
     GPU
    -0.82
    GPU
    -0.77
     gpu
    -0.66
     GPUs
    -0.52
    Searcher
    -0.52
    fluence
    -0.51
    ETER
    -0.51
     Wartawan
    -0.50
    factories
    -0.50
     passports
    -0.49
    POSITIVE LOGITS
    queryInterface
    0.62
     colorés
    0.53
    Portale
    0.52
    inkel
    0.51
     démocr
    0.51
    InvalidProtocol
    0.50
     méta
    0.49
     Мексичка
    0.49
     vidare
    0.49
     siyang
    0.48
    Activations Density 0.795%

    No Known Activations