© 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. 10151
    Prev
    Next
    INDEX
    Explanations

    to

    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
     InputDecoration
    -0.75
     choices
    -0.74
     choice
    -0.74
     Choose
    -0.73
     Choices
    -0.71
     wyboru
    -0.71
     memilih
    -0.68
    Zeneca
    -0.68
    tellers
    -0.68
    Choose
    -0.68
    POSITIVE LOGITS
     use
    0.52
     useAppContext
    0.46
     take
    0.44
    Viungo
    0.41
     took
    0.41
     utilize
    0.41
     wasn
    0.40
    InputTagHelper
    0.40
     cuanto
    0.40
     apply
    0.39
    Activations Density 0.028%

    No Known Activations