© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94365
    Prev
    Next
    INDEX
    Explanations

    argumentation

    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
    Cubit
    -0.49
     of
    -0.47
    AutoField
    -0.46
     مشين
    -0.46
    jarse
    -0.44
     yake
    -0.43
     جد
    -0.42
    knecht
    -0.41
    WebServlet
    -0.41
    RenderAtEndOf
    -0.40
    POSITIVE LOGITS
     that
    0.81
    LLocation
    0.68
    rungsseite
    0.63
    InteropServices
    0.61
     beautifully
    0.61
    icoot
    0.60
     forcefully
    0.59
     bahwa
    0.57
     estekak
    0.57
    #
    0.57
    Activations Density 0.001%

    No Known Activations