© 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. 97683
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    qrstuvwxyz
    -0.61
     Basket
    -0.59
     mourut
    -0.57
     désolés
    -0.55
     Dostupné
    -0.55
     Exactos
    -0.54
     définiti
    -0.51
    enderal
    -0.50
    ękuję
    -0.50
    seguida
    -0.49
    POSITIVE LOGITS
    NoSuchAlgorithm
    0.59
    AddTagHelper
    0.56
    Życiorys
    0.55
    RequiresApi
    0.53
    oa̍t
    0.52
    tock
    0.52
    ponses
    0.52
     TextStyle
    0.50
    LayoutStyle
    0.49
     الرياضيه
    0.49
    Activations Density 0.004%

    No Known Activations