© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2736
    Prev
    Next
    INDEX
    Explanations

    of

    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
    expandindo
    -0.78
    DataAnnotations
    -0.70
    WriteTagHelper
    -0.68
     ujednoznacz
    -0.66
    InputBorder
    -0.65
     '\\;'
    -0.65
     Mentions
    -0.61
     Efq
    -0.60
    ToFit
    -0.60
    iyle
    -0.60
    POSITIVE LOGITS
     来自
    0.42
     isInitialized
    0.40
     Gilman
    0.40
    orm
    0.39
    чну
    0.39
    ARM
    0.39
    LayoutStyle
    0.39
    enterOuterAlt
    0.39
    /*++
    0.38
    ghalaya
    0.38
    Activations Density 0.017%

    No Known Activations