© 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. 0-CLT-HP
    7. 97100
    Prev
    Next
    INDEX
    Explanations

    upstairs

    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
    STE
    -1.23
    zig
    -1.02
    rh
    -0.68
    دانشنامهٔ
    -0.57
    ecore
    -0.56
     "%"
    -0.52
    gole
    -0.52
     upstairs
    -0.49
     anzi
    -0.49
     plă
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.93
    JspWriter
    0.75
     resourceCulture
    0.75
     wireType
    0.73
     يتيمه
    0.68
    InputBorder
    0.66
    躇
    0.59
     Infórmanos
    0.57
     فريبيس
    0.57
    RenderAtEndOf
    0.56
    Activations Density 1.080%

    No Known Activations