© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90552
    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
    IBOutlet
    -0.65
    Portale
    -0.54
    WithMany
    -0.50
     getSystem
    -0.48
     APL
    -0.47
    guenos
    -0.46
    vės
    -0.46
     intptr
    -0.45
    Pautan
    -0.44
     EGL
    -0.43
    POSITIVE LOGITS
    出版年
    0.74
    WebElementEntity
    0.66
     CreateTagHelper
    0.64
    timewa
    0.62
     estekak
    0.62
    matchCondition
    0.60
    LabelTagHelper
    0.60
     المعرف
    0.60
    "));
    
    0.58
     stoichio
    0.58
    Activations Density 0.071%

    No Known Activations