© 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. 9793
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     quæ
    -0.91
    AndEndTag
    -0.88
     Paglinawan
    -0.73
     iſt
    -0.72
    CloseOperation
    -0.71
    FormTagHelper
    -0.70
    antaranya
    -0.69
    harapkan
    -0.67
     auffi
    -0.67
    astify
    -0.64
    POSITIVE LOGITS
     experience
    0.56
     kasarigan
    0.52
    methe
    0.52
     popsic
    0.51
     correctes
    0.50
    Experience
    0.48
     stretchy
    0.48
     better
    0.48
     jut
    0.48
     epic
    0.48
    Activations Density 0.075%

    No Known Activations