© 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. 1-CLT-HP
    7. 568
    Prev
    Next
    INDEX
    Explanations

    friendship/relationships

    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
     científicas
    -0.58
    Adverti
    -0.48
     investigating
    -0.46
     przecież
    -0.46
    imported
    -0.44
     ביותר
    -0.43
     touristes
    -0.41
     imidlertid
    -0.41
    investigation
    -0.41
     elles
    -0.40
    POSITIVE LOGITS
    ьаж
    0.91
     Paglinawan
    0.78
    Vidite
    0.78
    AccessorTable
    0.78
     InputDecoration
    0.73
     chi̍t
    0.70
     CreateTagHelper
    0.68
    épendance
    0.65
    談社
    0.65
    脚注の使い方
    0.65
    Activations Density 0.051%

    No Known Activations