© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94907
    Prev
    Next
    INDEX
    Explanations

    casual conversations

    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
     оригіналу
    -0.69
    antaine
    -0.57
     demonstration
    -0.55
    jenner
    -0.54
     burden
    -0.54
    yntaxException
    -0.54
    -------
    -0.53
    audrait
    -0.50
    довой
    -0.50
    ViewImports
    -0.50
    POSITIVE LOGITS
     bonté
    0.60
    Lähteet
    0.59
    Спољашње
    0.58
     lenker
    0.56
    følgelig
    0.53
    ximately
    0.52
    sidemargin
    0.51
    ExtendWith
    0.51
    quels
    0.51
    surveys
    0.51
    Activations Density 0.011%

    No Known Activations