© 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. 0-CLT-HP
    7. 41540
    Prev
    Next
    INDEX
    Explanations

    internet strings

    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
    tson
    -0.98
     useRouter
    -0.64
    ondon
    -0.61
    はじめに
    -0.60
    клопе
    -0.54
     noDo
    -0.54
    HasForeignKey
    -0.54
    InSection
    -0.54
    Czytaj
    -0.52
    abestanden
    -0.51
    POSITIVE LOGITS
    ьаж
    0.71
    ThroughAttribute
    0.67
    amoan
    0.64
     Italijanski
    0.61
    modelBuilder
    0.58
    ses
    0.57
     trúc
    0.57
    ">//
    0.57
    Vidite
    0.56
    HideFlags
    0.55
    Activations Density 0.153%

    No Known Activations