© 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. 3346
    Prev
    Next
    INDEX
    Explanations

    Dates

    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
      
    -0.41
    1
    -0.40
    о
    -0.39
     о
    -0.39
    ・
    -0.39
    ノ
    -0.38
    자
    -0.38
    ğı
    -0.37
    性
    -0.37
    コ
    -0.36
    POSITIVE LOGITS
    +:+
    0.91
    AndEndTag
    0.87
    
    0.86
    __':
    0.85
    ViewFeatures
    0.84
    HostException
    0.83
     snippetHide
    0.83
     ویکی‌پدیا
    0.81
     wikipagina
    0.79
    sizeCache
    0.78
    Activations Density 0.020%

    No Known Activations