© 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. 5-CLT-HP
    7. 93031
    Prev
    Next
    INDEX
    Explanations

    river

    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
    complexContent
    -0.93
    Personensuche
    -0.88
     Roskov
    -0.78
     defaultstate
    -0.75
    tagHelperRunner
    -0.74
    出版年
    -0.73
     ویکی‌پدیا
    -0.73
     surla
    -0.72
    WireFormatLite
    -0.68
    OGND
    -0.66
    POSITIVE LOGITS
     Mara
    0.50
    Ấ
    0.49
    المنا
    0.49
    Vie
    0.46
    gelijk
    0.45
    Palindrome
    0.44
     Kü
    0.44
     tänka
    0.43
    kü
    0.42
    バリー
    0.41
    Activations Density 0.003%

    No Known Activations