© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 5019
    Prev
    Next
    INDEX
    Explanations

    know

    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
    
    -0.77
    EndGlobalSection
    -0.72
     fatale
    -0.58
    IUrlHelper
    -0.56
     correctes
    -0.56
     Digestion
    -0.55
    ophones
    -0.55
     NgModule
    -0.54
    providedIn
    -0.54
    better
    -0.54
    POSITIVE LOGITS
    +#+
    0.55
     autorytatywna
    0.52
    nalités
    0.52
    pearing
    0.50
     ControllerBase
    0.50
    npmjs
    0.47
    openzeppelin
    0.47
     helping
    0.43
    CppMethod
    0.42
     hadi
    0.41
    Activations Density 0.005%

    No Known Activations