© 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. 5509
    Prev
    Next
    INDEX
    Explanations

    global locations/issues

    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
    出版年
    -0.69
     CreateTagHelper
    -0.64
    XMLSchema
    -0.59
    Personendaten
    -0.58
     للاسماء
    -0.57
    valdi
    -0.57
    Portale
    -0.57
    TagMode
    -0.56
    SOUNDBITE
    -0.56
     Paglinawan
    -0.54
    POSITIVE LOGITS
    ’
    0.50
     världen
    0.47
     romántica
    0.47
     milliers
    0.47
    seamnă
    0.45
    penuhi
    0.45
     anuales
    0.45
     juist
    0.44
     cejas
    0.43
    ])));
    0.43
    Activations Density 0.001%

    No Known Activations