© 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. 4-CLT-HP
    7. 526
    Prev
    Next
    INDEX
    Explanations

    ability

    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
    
    -0.56
    ’
    -0.55
     or
    -0.53
     kader
    -0.52
     ligiloj
    -0.50
    occasione
    -0.49
     propOrder
    -0.49
    ontan
    -0.48
     arşivlendi
    -0.48
    then
    -0.47
    POSITIVE LOGITS
    RegressionTest
    0.66
    بوابة
    0.59
    createServer
    0.58
    MLLoader
    0.54
    IZABETH
    0.52
    Identyfik
    0.52
    iseur
    0.51
    subplot
    0.51
    ussis
    0.50
    Bibliograf
    0.50
    Activations Density 0.003%

    No Known Activations