© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91193
    Prev
    Next
    INDEX
    Explanations

    code/usernames

    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
    ibi
    -1.38
    bitur
    -1.05
     AssemblyCompany
    -0.99
    AddTagHelper
    -0.90
     NSCoder
    -0.81
    ViewImports
    -0.80
    AnimationsModule
    -0.80
    belle
    -0.79
    脚注の使い方
    -0.78
    IBI
    -0.76
    POSITIVE LOGITS
     extension
    0.50
     bes
    0.44
     back
    0.43
    steven
    0.42
     this
    0.42
     group
    0.41
    ё
    0.40
     Ext
    0.40
     let
    0.40
     return
    0.40
    Activations Density 0.909%

    No Known Activations