© 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. 0-CLT-HP
    7. 95294
    Prev
    Next
    INDEX
    Explanations

    Inner/outer

    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
    [
    -0.50
     [
    -0.49
    protoc
    -0.48
    QPalette
    -0.43
     bu
    -0.43
     {
    -0.43
    [\
    -0.43
    anser
    -0.42
    {
    -0.42
     \
    -0.42
    POSITIVE LOGITS
    ´)
    0.75
     Мексичка
    0.73
    انيف
    0.73
    expandindo
    0.71
     referenties
    0.66
     theſe
    0.65
     ſeveral
    0.63
     LoggerFactory
    0.63
     kaarangay
    0.62
     سكانية
    0.62
    Activations Density 0.043%

    No Known Activations