© 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. 4-CLT-HP
    7. 2336
    Prev
    Next
    INDEX
    Explanations

    to

    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
    adaptiveStyles
    -0.75
    findpost
    -0.68
    存于互联网档案馆
    -0.68
    出版年
    -0.64
    fillType
    -0.61
    rawDesc
    -0.56
     TPE
    -0.55
     houſe
    -0.54
    djangoproject
    -0.54
     متعلقه
    -0.53
    POSITIVE LOGITS
    Попис
    0.59
    prite
    0.57
     مرئيه
    0.55
     thử
    0.52
    épreuve
    0.52
    Express
    0.52
     Express
    0.50
     express
    0.50
    bilité
    0.49
    السكان
    0.48
    Activations Density 0.002%

    No Known Activations