© 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. 5-CLT-HP
    7. 96549
    Prev
    Next
    INDEX
    Explanations

    technical discussions and conversations

    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
    StoreMessageInfo
    -0.67
     بيها
    -0.66
    ImageContext
    -0.64
     typelib
    -0.62
    LayoutStyle
    -0.59
     صوتيه
    -0.58
     fieldNum
    -0.56
     bezeichneter
    -0.55
    +:+
    -0.54
     GeoNames
    -0.53
    POSITIVE LOGITS
     $
    0.54
     
    0.54
    ROZ
    0.46
     millions
    0.46
    kolo
    0.44
    dsl
    0.43
    romic
    0.43
    interopRequire
    0.42
     true
    0.42
    xnn
    0.42
    Activations Density 0.001%

    No Known Activations