© 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. 0-CLT-HP
    7. 41088
    Prev
    Next
    INDEX
    Explanations

    why

    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
     why
    -2.17
    why
    -1.59
     hvorfor
    -1.43
     varför
    -1.42
     pourquoi
    -1.41
     waarom
    -1.39
     Why
    -1.34
    Why
    -1.29
     mengapa
    -1.29
     warum
    -1.27
    POSITIVE LOGITS
    CppMethod
    0.68
    InputTagHelper
    0.66
    InvalidProtocol
    0.62
    webElementXpaths
    0.60
    GEBURTSDATUM
    0.60
     dig
    0.59
     Италијани
    0.59
     commercial
    0.58
     radical
    0.58
     programmes
    0.57
    Activations Density 0.170%

    No Known Activations