© 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. 5-CLT-HP
    7. 96458
    Prev
    Next
    INDEX
    Explanations

    s

    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
     disambiguazione
    -0.73
    xtext
    -0.68
     للاسماء
    -0.65
    endix
    -0.61
    يكب
    -0.59
    يميديا
    -0.57
     affichés
    -0.54
     mergeFrom
    -0.52
     inspire
    -0.52
    rawDesc
    -0.52
    POSITIVE LOGITS
    ArgumentParser
    0.57
    IntoConstraints
    0.50
     cref
    0.46
     werkzaam
    0.45
    __':
    0.44
     elett
    0.44
    hadores
    0.43
    gonic
    0.43
    crollView
    0.43
    '}}
    0.43
    Activations Density 0.005%

    No Known Activations