© 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. 10095
    Prev
    Next
    INDEX
    Explanations

    Language and linguistics

    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
     nahilalakip
    -0.84
    StoryboardSegue
    -0.84
    ViewFeatures
    -0.81
    kháu
    -0.77
    AddTagHelper
    -0.77
    tagext
    -0.73
     للاسماء
    -0.71
    ंदीखरीदारी
    -0.71
     دیکھیے
    -0.71
     Signalez
    -0.69
    POSITIVE LOGITS
    itum
    0.53
     forming
    0.52
    hips
    0.48
     Del
    0.48
    ages
    0.48
    طه
    0.48
     نقل
    0.47
     creating
    0.47
    acja
    0.47
     moving
    0.45
    Activations Density 0.017%

    No Known Activations