© 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. 2500
    Prev
    Next
    INDEX
    Explanations

    partially

    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
    AsUp
    -0.73
     متعلقه
    -0.64
     تانيه
    -0.61
     Normdatei
    -0.61
     doucement
    -0.60
     colorés
    -0.60
     guère
    -0.59
     définiti
    -0.59
     spesa
    -0.59
     marquées
    -0.58
    POSITIVE LOGITS
     or
    1.02
     или
    0.69
     oder
    0.66
    或
    0.66
     eller
    0.66
     atau
    0.62
    或者
    0.62
     hoặc
    0.62
    หรือ
    0.60
     või
    0.59
    Activations Density 0.002%

    No Known Activations