© 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. 5021
    Prev
    Next
    INDEX
    Explanations

    Snippets of text/code

    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
    μφωνα
    -0.63
     للاسماء
    -0.61
     كومونز
    -0.56
    cipar
    -0.54
     препратки
    -0.53
    Abit
    -0.51
     समीक्षक
    -0.50
     CreateTagHelper
    -0.50
    脚注の使い方
    -0.50
     thù
    -0.48
    POSITIVE LOGITS
    poque
    0.58
    IDEN
    0.50
    QMetaType
    0.49
    ersk
    0.49
    funeralhome
    0.48
    хьтан
    0.48
    MethodType
    0.48
    contentLoaded
    0.47
    UnsafeEnabled
    0.46
    tisch
    0.46
    Activations Density 0.002%

    No Known Activations