© 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. 911
    Prev
    Next
    INDEX
    Explanations

    defined

    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
    TargetException
    -0.59
    Autoritní
    -0.57
     فريبيس
    -0.55
    posedge
    -0.54
    ITIS
    -0.52
    betic
    -0.52
     collectivités
    -0.49
     scienza
    -0.48
     main
    -0.48
    bts
    -0.48
    POSITIVE LOGITS
     here
    0.92
    here
    0.68
     as
    0.68
     disini
    0.60
     Here
    0.59
     AspNetCore
    0.57
     herein
    0.56
     aquí
    0.56
    Here
    0.55
     aici
    0.52
    Activations Density 0.002%

    No Known Activations