© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97834
    Prev
    Next
    INDEX
    Explanations

    descriptions of signs/labels

    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
     pinulongan
    -0.76
    aarrggbb
    -0.63
     Waray
    -0.55
     الحره
    -0.54
     PrintWriter
    -0.50
    supposed
    -0.50
     hóspedes
    -0.49
    yeezy
    -0.47
     useDispatch
    -0.47
    openSession
    -0.46
    POSITIVE LOGITS
    تقاوى
    0.62
     ویکی‌پدیا
    0.55
    KURZBESCHREIBUNG
    0.53
    انيف
    0.50
     تضيفلها
    0.50
    setVerticalGroup
    0.48
    AutoScale
    0.47
    ]}\
    0.47
    tagHelperRunner
    0.46
    XmlIgnore
    0.46
    Activations Density 0.002%

    No Known Activations