© 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. 5-CLT-HP
    4. 96678
    Prev
    Next
    INDEX
    Explanations

    with

    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
     للمعارف
    -0.47
     بخشی
    -0.47
    ">'+
    -0.47
     encontraban
    -0.43
     roues
    -0.40
    izeit
    -0.40
     abundante
    -0.39
    tamment
    -0.39
     imageNamed
    -0.39
    runOnUiThread
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.87
     CreateTagHelper
    0.80
     friends
    0.71
    AndEndTag
    0.71
    NameInMap
    0.68
     AssemblyTitle
    0.67
    UnknownFieldSet
    0.66
     propOrder
    0.65
     saites
    0.65
     toddlers
    0.65
    Activations Density 0.001%

    No Known Activations