© 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. 93618
    Prev
    Next
    INDEX
    Explanations

    for

    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
     their
    -0.55
    either
    -0.54
     its
    -0.53
     or
    -0.53
     the
    -0.51
    的一种
    -0.49
    Их
    -0.49
    their
    -0.48
     vanligt
    -0.48
     Either
    -0.48
    POSITIVE LOGITS
     esternos
    0.81
     مرئيه
    0.80
    enumii
    0.79
     OFDb
    0.77
     فريبيس
    0.76
     Audiodateien
    0.75
    :
    0.68
     ویکی‌پدیا
    0.67
    ✨:
    0.65
    MessageTagHelper
    0.63
    Activations Density 0.002%

    No Known Activations