© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 57
    Prev
    Next
    INDEX
    Explanations

    a

    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
     different
    -0.54
     related
    -0.54
    yntaxException
    -0.49
    urante
    -0.48
    войства
    -0.47
     higher
    -0.46
    bless
    -0.46
    
    -0.45
     client
    -0.45
     fixed
    -0.45
    POSITIVE LOGITS
     الرياضيه
    0.68
    
    0.66
     numberOfRows
    0.59
     חיצוניים
    0.57
     hectare
    0.54
    VersionUID
    0.52
     half
    0.51
     peu
    0.51
    ymce
    0.51
     HALF
    0.50
    Activations Density 0.002%

    No Known Activations