© 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. 0-CLT-HP
    7. 1475
    Prev
    Next
    INDEX
    Explanations

    Random text blocks

    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
    /**
    -0.49
     Ireland
    -0.46
    jsonwebtoken
    -0.46
     createState
    -0.46
     a
    -0.46
    SqlClient
    -0.45
     Angleterre
    -0.45
    恥
    -0.45
    计
    -0.44
     A
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
    出版年
    0.72
     виправивши
    0.68
     дописавши
    0.65
     Vikipedi
    0.65
     Dafür
    0.64
     betweenstory
    0.63
    setVerticalGroup
    0.62
    ANTLR
    0.61
    EndProject
    0.59
    Activations Density 0.455%

    No Known Activations