© 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. 4-CLT-HP
    7. 1241
    Prev
    Next
    INDEX
    Explanations

    character

    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
    ist
    -0.62
    Спасылкі
    -0.46
    IUrlHelper
    -0.42
    ContentAsync
    -0.42
    ists
    -0.41
    skal
    -0.41
     "|
    -0.40
     Zusammen
    -0.40
    Viungo
    -0.40
    Халык
    -0.39
    POSITIVE LOGITS
    zzleHttp
    0.74
    SizeF
    0.69
    neuf
    0.69
    Демографія
    0.64
    StandardCharsets
    0.62
     BEHAV
    0.60
     OnInit
    0.60
    istoitu
    0.59
    AddHtmlAttribute
    0.59
    bootstrapcdn
    0.59
    Activations Density 0.002%

    No Known Activations