© 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. 90908
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     CreateTagHelper
    -0.89
    makeConstraints
    -0.81
    IsContent
    -0.79
     ExecuteAsync
    -0.76
    webElementXpaths
    -0.71
     насељу
    -0.70
    Geplaatst
    -0.69
    StoreMessageInfo
    -0.69
     AssemblyCompany
    -0.68
    WriteTagHelper
    -0.66
    POSITIVE LOGITS
     gehouden
    0.69
     particulières
    0.47
     säkert
    0.47
     inalámb
    0.47
     fondament
    0.46
     rús
    0.45
     conscientes
    0.45
     столько
    0.45
     tiennent
    0.44
     atuais
    0.44
    Activations Density 0.013%

    No Known Activations