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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4832
    Prev
    Next
    INDEX
    Explanations

    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
     NSCoder
    -1.09
    MemoryWarning
    -1.09
    enumi
    -1.07
    localctx
    -0.99
    RetentionPolicy
    -0.96
    ScopeManager
    -0.93
     typelib
    -0.93
    脚注の使い方
    -0.91
    contentLoaded
    -0.90
    InjectAttribute
    -0.88
    POSITIVE LOGITS
    arga
    0.46
     S
    0.44
     di
    0.41
    dit
    0.41
    File
    0.39
    GetInstance
    0.39
    部屋
    0.39
    oga
    0.39
     J
    0.39
    染
    0.39
    Activations Density 0.001%

    No Known Activations