© 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. 9699
    Prev
    Next
    INDEX
    Explanations

    at

    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
    aarrggbb
    -0.62
    ndice
    -0.53
     duquel
    -0.52
     recevez
    -0.52
    nsyn
    -0.52
    ⋙
    -0.51
     abstrait
    -0.50
     vọng
    -0.50
     scolaires
    -0.49
     parvenir
    -0.49
    POSITIVE LOGITS
     Winaray
    0.59
     للمعارف
    0.58
    AddTagHelper
    0.57
     AssemblyVersion
    0.56
    IContainer
    0.53
     ***!
    0.53
     AssemblyCompany
    0.52
     UnityEditor
    0.51
    ModelAdmin
    0.51
     MainAxisSize
    0.50
    Activations Density 0.064%

    No Known Activations