© 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. 96784
    Prev
    Next
    INDEX
    Explanations

    using import

    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
    مح
    -0.50
     mengan
    -0.48
    žin
    -0.46
     Wars
    -0.45
     érde
    -0.43
    ПИ
    -0.42
    宿
    -0.42
    rit
    -0.42
    敗
    -0.42
    vician
    -0.41
    POSITIVE LOGITS
    WithIOException
    0.88
    Sucesor
    0.76
     useAppContext
    0.76
     beginnetje
    0.68
    ніципалі
    0.68
    WEBPACK
    0.68
     تضيفلها
    0.66
    )‏
    0.66
     Monark
    0.66
    XMLSchema
    0.66
    Activations Density 0.112%

    No Known Activations