© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91687
    Prev
    Next
    INDEX
    Explanations

    boundary

    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
    SequentialGroup
    -0.68
    RectangleBorder
    -0.63
     referência
    -0.63
    romptu
    -0.62
    ẻo
    -0.60
    őben
    -0.57
     afterward
    -0.56
    InputBorder
    -0.55
    complexContent
    -0.54
    LEncoder
    -0.54
    POSITIVE LOGITS
     MonoBehaviour
    0.62
    omitempty
    0.57
    municipi
    0.47
     EDA
    0.45
    WSGI
    0.45
    apnews
    0.45
    Попис
    0.44
     typelib
    0.43
    *************/
    0.43
     שוליים
    0.43
    Activations Density 0.001%

    No Known Activations