© 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. 419
    Prev
    Next
    INDEX
    Explanations

    English text

    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
     venons
    -0.70
     Ceremonies
    -0.63
    LayoutStyle
    -0.62
    Приятного
    -0.61
     feroit
    -0.61
    mặt
    -0.60
     Prophecy
    -0.59
    ViewFeatures
    -0.59
     BoxFit
    -0.59
     sacré
    -0.59
    POSITIVE LOGITS
     use
    0.50
     application
    0.49
     process
    0.47
     only
    0.47
    twimg
    0.43
     term
    0.42
    لينكات
    0.42
    ViewSet
    0.42
    saraba
    0.41
     AssemblyTitle
    0.40
    Activations Density 0.001%

    No Known Activations