© 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. 5-CLT-HP
    7. 94864
    Prev
    Next
    INDEX
    Explanations

    Information/data processing

    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
     الحره
    -0.86
     فريبيس
    -0.79
    ImageContext
    -0.78
    ThroughAttribute
    -0.77
     cherchés
    -0.72
    ########.
    -0.70
    StoryboardSegue
    -0.70
    LookAnd
    -0.68
    TintMode
    -0.67
     unknownFields
    -0.65
    POSITIVE LOGITS
     betweenstory
    0.42
    ViewImports
    0.42
    odeficiency
    0.34
     MenuView
    0.33
     Italijani
    0.32
     χρή
    0.32
     chyb
    0.31
     intellectuelle
    0.31
     cár
    0.31
     cérami
    0.30
    Activations Density 0.012%

    No Known Activations