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. 74187
    Prev
    Next
    INDEX
    Explanations

    Technical and formal writing

    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
     referenties
    -0.84
     kasarigan
    -0.71
     NSCoder
    -0.68
     صوتيه
    -0.68
     насељу
    -0.67
    TypedDataSet
    -0.66
     Wikimedijinoj
    -0.65
    انيف
    -0.64
     chi̍t
    -0.63
     noDo
    -0.63
    POSITIVE LOGITS
    wyczaj
    0.40
    ọi
    0.39
    elser
    0.39
    keer
    0.38
    jores
    0.37
    fels
    0.37
    copg
    0.37
    TableCell
    0.36
    Par
    0.36
    opardy
    0.36
    Activations Density 0.003%

    No Known Activations