© 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. 4-CLT-HP
    7. 4970
    Prev
    Next
    INDEX
    Explanations

    web scraping

    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
    TagMode
    -0.51
    zzá
    -0.50
    otherapy
    -0.49
    i
    -0.49
    IntoConstraints
    -0.47
    发表于
    -0.47
    ians
    -0.46
    ↻
    -0.45
    iksi
    -0.45
    inars
    -0.45
    POSITIVE LOGITS
     ErrIntOverflow
    0.56
    DeleteBehavior
    0.52
     Monfieur
    0.51
     onAnimation
    0.50
    parque
    0.49
    ReusableCell
    0.48
    wiſe
    0.47
     myſelf
    0.46
     ymm
    0.45
     Dede
    0.45
    Activations Density 0.003%

    No Known Activations