© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46024
    Prev
    Next
    INDEX
    Explanations

    common

    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
     defaultstate
    -0.54
     common
    -0.54
    igshid
    -0.47
    Common
    -0.47
    weich
    -0.45
    iapkan
    -0.45
     érde
    -0.44
     Вікіпе
    -0.44
    common
    -0.44
     Common
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.63
    land
    0.62
    age
    0.58
    EDEFAULT
    0.58
    IInterface
    0.58
    RenderAtEndOf
    0.57
    nalité
    0.57
    énagement
    0.57
    ItemBackground
    0.57
    nesses
    0.56
    Activations Density 0.018%

    No Known Activations