© 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. 2317
    Prev
    Next
    INDEX
    Explanations

    The

    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
     autres
    -0.40
     outros
    -0.39
     altres
    -0.37
    Others
    -0.36
    齐
    -0.35
     EMS
    -0.35
    others
    -0.35
    including
    -0.35
    อื่น
    -0.34
    INCLUDING
    -0.33
    POSITIVE LOGITS
    EndGlobalSection
    0.91
    
    0.78
    Климат
    0.77
     فريبيس
    0.75
     GenerationType
    0.73
    prüche
    0.73
    دانشنامهٔ
    0.73
    )|^{
    0.71
    rungsseite
    0.71
    Chham
    0.71
    Activations Density 0.001%

    No Known Activations