© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92826
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ScopeManager
    -0.78
    تقاوى
    -0.65
    makeConstraints
    -0.62
    AddTagHelper
    -0.61
    createStatement
    -0.60
    
    -0.60
     ourselves
    -0.60
    [];
    -0.59
     yourselves
    -0.57
    NgModule
    -0.57
    POSITIVE LOGITS
     judiciales
    0.56
    RUnlock
    0.46
     grund
    0.44
    当场
    0.44
     urbanas
    0.44
    PerformLayout
    0.43
     zů
    0.43
     grunn
    0.43
     nakalista
    0.43
    érience
    0.41
    Activations Density 0.045%

    No Known Activations