© 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. 2714
    Prev
    Next
    INDEX
    Explanations

    ciful

    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
    webElementXpaths
    -0.61
     ComVisible
    -0.58
    impan
    -0.55
     насељу
    -0.55
     تعدى
    -0.54
    ligare
    -0.52
     geçen
    -0.52
     poveznice
    -0.52
    aarrggbb
    -0.51
    :+:
    -0.49
    POSITIVE LOGITS
     hitter
    0.54
     bombed
    0.54
    ]),
    
    0.52
     @"";
    0.52
     Nós
    0.51
    wers
    0.51
     companyId
    0.49
    éric
    0.49
     hatchery
    0.47
     NSCoder
    0.47
    Activations Density 0.003%

    No Known Activations