© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6206
    Prev
    Next
    INDEX
    Explanations

    who

    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
    Negative Logits
    featureID
    -0.62
    IUrlHelper
    -0.55
    ագրություններ
    -0.50
    num
    -0.43
    URLConnection
    -0.42
    then
    -0.41
     femeninos
    -0.41
     아니
    -0.41
    تقاوى
    -0.39
     Ashby
    -0.39
    POSITIVE LOGITS
     thinks
    1.00
     loves
    0.96
     wants
    0.95
     forgets
    0.94
     believes
    0.94
     hates
    0.89
     wonders
    0.88
     expects
    0.85
     hopes
    0.85
     finds
    0.85
    Activations Density 0.002%

    No Known Activations