© 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. 5690
    Prev
    Next
    INDEX
    Explanations

    medical risk factors

    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
    ﴿
    -0.68
    <bos>
    -0.62
    \"");
    -0.58
    )];
    -0.55
    ')")
    -0.54
    yntaxException
    -0.54
    ']))
    -0.53
    PreferredItem
    -0.53
    ết
    -0.52
     spoil
    -0.52
    POSITIVE LOGITS
     neutre
    0.63
     fallu
    0.59
     externi
    0.59
     démocratie
    0.57
     épaules
    0.54
     prossima
    0.52
    Predecesor
    0.52
     verksamhet
    0.52
    معلومات
    0.51
     supérieurs
    0.50
    Activations Density 0.002%

    No Known Activations