© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1518
    Prev
    Next
    INDEX
    Explanations

    is

    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
    PerformLayout
    -0.59
     Paglinawan
    -0.58
     виправивши
    -0.55
    racene
    -0.52
    tagHelperRunner
    -0.50
    brough
    -0.49
    shad
    -0.49
    atop
    -0.49
    AntiForgeryToken
    -0.49
     ***!
    -0.49
    POSITIVE LOGITS
     understands
    0.63
    Erreferentziak
    0.61
     unclear
    0.58
     hoped
    0.56
     StatelessWidget
    0.55
     hoping
    0.54
    Források
    0.54
     understood
    0.53
     understand
    0.52
     understanding
    0.52
    Activations Density 0.013%

    No Known Activations