© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94240
    Prev
    Next
    INDEX
    Explanations

    Japanese particle は

    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
     is
    -1.13
    saraba
    -0.77
    TypedDataSet
    -0.60
    i
    -0.48
    Spoljašnje
    -0.48
    DrawerToggle
    -0.47
    cektir
    -0.47
    beat
    -0.46
    辺
    -0.46
    :].
    -0.46
    POSITIVE LOGITS
    Datuak
    0.79
    HtmlAttribute
    0.63
    rrggbb
    0.62
    Xaml
    0.61
    RectangleBorder
    0.60
     Superhosts
    0.59
    IntoConstraints
    0.59
    weck
    0.56
     صوتيه
    0.56
    бята
    0.55
    Activations Density 1.246%

    No Known Activations