© 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. 4-CLT-HP
    7. 109
    Prev
    Next
    INDEX
    Explanations

    jury

    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
     ostavi
    -0.66
    ChildScrollView
    -0.62
     Drapeau
    -0.56
    sort
    -0.55
    zzleHttp
    -0.53
     CommonModule
    -0.51
    sor
    -0.50
    фера
    -0.50
    URIComponent
    -0.50
     newOwner
    -0.50
    POSITIVE LOGITS
     duty
    0.68
     DUTY
    0.59
    setVerticalGroup
    0.57
    Duty
    0.57
    duty
    0.56
    tifully
    0.55
     CreateTagHelper
    0.54
    protoc
    0.54
     Duty
    0.53
     viață
    0.52
    Activations Density 0.002%

    No Known Activations