© 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. 20-CLT-HP
    4. 74977
    Prev
    Next
    INDEX
    Explanations

    Code/formal writing

    np_max-act-logits · 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
     فريبيس
    -0.70
     clubs
    -0.67
     museums
    -0.65
     councils
    -0.62
     Boards
    -0.62
     boards
    -0.61
     "..\..\..\
    -0.60
     hospitals
    -0.58
    Portale
    -0.57
     Councils
    -0.57
    POSITIVE LOGITS
     contextLoads
    0.69
    eseorang
    0.63
    那个
    0.62
     vœux
    0.58
    runOnUiThread
    0.58
     compétences
    0.58
     peines
    0.57
     একটি
    0.57
    inę
    0.56
    Flows
    0.56
    Activations Density 0.002%

    No Known Activations