Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74222
    Prev
    Next
    INDEX
    Explanations

    Resolution/Definition

    np_max-act-logits · 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
     tắc
    -0.58
     surla
    -0.55
     Eccl
    -0.52
    AndEndTag
    -0.52
     Flavor
    -0.51
    silen
    -0.50
    rrggbb
    -0.49
    LayoutStyle
    -0.49
     DEPTH
    -0.48
     Guimarães
    -0.48
    POSITIVE LOGITS
     res
    0.77
    res
    0.71
     definition
    0.63
    解
    0.60
    Res
    0.59
     reso
    0.58
    annica
    0.57
     resul
    0.57
    ösung
    0.55
    gelöst
    0.55
    Activations Density 0.002%

    No Known Activations