© 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. 0-CLT-HP
    7. 94684
    Prev
    Next
    INDEX
    Explanations

    Provide

    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
    +#+#
    -1.27
     مشين
    -1.13
     AssemblyCulture
    -1.11
    EndProject
    -1.09
     Мексичка
    -1.07
    ImageContext
    -1.05
    :✨
    -1.01
    Personendaten
    -1.01
     Offer
    -1.00
    tagHelperRunner
    -1.00
    POSITIVE LOGITS
     
    0.77
     Quick
    0.61
     may
    0.56
     General
    0.56
     He
    0.54
     A
    0.52
     High
    0.52
    ing
    0.51
     must
    0.50
     Super
    0.50
    Activations Density 0.056%

    No Known Activations