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. 74468
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    nami
    -0.51
    HomeAsUpEnabled
    -0.46
     digress
    -0.45
     نزد
    -0.44
    JspWriter
    -0.41
    upassen
    -0.40
     πέ
    -0.40
    طي
    -0.40
    nables
    -0.40
    BOD
    -0.39
    POSITIVE LOGITS
    WithIOException
    0.73
    ьаж
    0.69
     Paglinawan
    0.66
    Попис
    0.65
     الاطلاع
    0.63
    GOTREF
    0.63
    Демографія
    0.59
    حياته
    0.59
    حياتها
    0.57
    ագրություններ
    0.57
    Activations Density 0.001%

    No Known Activations