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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74480
    Prev
    Next
    INDEX
    Explanations

    Code and web references

    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
     ainfi
    -0.85
     habituellement
    -0.79
     disambiguazione
    -0.78
    tagez
    -0.77
     againſt
    -0.76
     généraux
    -0.74
    μβρίου
    -0.72
    Décès
    -0.71
     auffi
    -0.70
     fréquence
    -0.70
    POSITIVE LOGITS
    MemoryWarning
    0.54
     M
    0.43
     mo
    0.42
    jspx
    0.41
     m
    0.41
     T
    0.40
    cla
    0.40
    тала
    0.39
    able
    0.38
    vores
    0.37
    Activations Density 0.021%

    No Known Activations