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. 74213
    Prev
    Next
    INDEX
    Explanations

    Technical/informative texts

    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
    ArgsConstructor
    -0.85
    <?
    -0.77
    Espèce
    -0.71
     EconPapers
    -0.69
    batore
    -0.68
     morire
    -0.68
     Heywood
    -0.68
    Rujuakan
    -0.68
     AssemblyCulture
    -0.67
     iNdEx
    -0.65
    POSITIVE LOGITS
     tr
    0.57
    tr
    0.49
     can
    0.48
     trunk
    0.48
    Can
    0.46
     Can
    0.45
     main
    0.44
     south
    0.42
     tru
    0.41
     bole
    0.40
    Activations Density 0.000%

    No Known Activations