© 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. 322
    Prev
    Next
    INDEX
    Explanations

    cold weather

    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
     Италијани
    -0.80
     propOrder
    -0.77
    IContainer
    -0.76
     ProtoMessage
    -0.75
    WithIOException
    -0.72
     Italijani
    -0.70
     المعيارى
    -0.68
    +#+#
    -0.68
    XmlAccessType
    -0.67
     disambiguazione
    -0.66
    POSITIVE LOGITS
    mailto
    0.45
    PerformLayout
    0.43
    deman
    0.42
    nip
    0.39
    ParallelGroup
    0.39
     CURLOPT
    0.39
    ury
    0.39
    fier
    0.38
    flg
    0.38
    djangoproject
    0.38
    Activations Density 0.001%

    No Known Activations