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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96599
    Prev
    Next
    INDEX
    Explanations

    places

    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
     ovi
    -0.55
    ฒ
    -0.55
    wpi
    -0.54
    rawtypes
    -0.54
     démocratie
    -0.54
     experimentation
    -0.53
    nữ
    -0.53
    berdayakan
    -0.52
     Experimental
    -0.51
     LatLng
    -0.51
    POSITIVE LOGITS
     cz
    0.48
    Diwedd
    0.46
     Wentworth
    0.45
    ագրություններ
    0.45
    Hauptartikel
    0.45
    endientes
    0.44
    Rhestr
    0.44
     Tart
    0.44
     Fizz
    0.42
    maßen
    0.42
    Activations Density 0.002%

    No Known Activations