© 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. 4653
    Prev
    Next
    INDEX
    Explanations

    Trinity

    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
     Waray
    -0.56
    Coordonnées
    -0.55
    Portale
    -0.49
     controlled
    -0.49
    volent
    -0.48
    
    -0.48
    álogo
    -0.48
     fears
    -0.47
    wnicy
    -0.47
    toMatchSnapshot
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.65
    makeText
    0.60
    CORBA
    0.59
     Alps
    0.57
     StatefulWidget
    0.56
    InputBorder
    0.55
    webElementXpaths
    0.55
    AddHtmlAttribute
    0.54
    mergeFrom
    0.54
     FontWeight
    0.52
    Activations Density 0.029%

    No Known Activations