© 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. 92282
    Prev
    Next
    INDEX
    Explanations

    emotions and thoughts

    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
     of
    -0.59
     själva
    -0.51
    vogel
    -0.47
     composants
    -0.47
     topik
    -0.47
    maksud
    -0.46
     fjer
    -0.46
     
    -0.46
     times
    -0.45
    ),
    -0.45
    POSITIVE LOGITS
     Roskov
    1.11
    Diweddarwch
    1.02
     AssemblyCulture
    0.84
     betweenstory
    0.84
    IsMutable
    0.82
     beginnetje
    0.79
     дописавши
    0.78
     NSCoder
    0.78
    EndProject
    0.75
     resourceCulture
    0.75
    Activations Density 0.094%

    No Known Activations