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. 74320
    Prev
    Next
    INDEX
    Explanations

    Filenames or code

    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
    новништво
    -0.54
     im
    -0.53
    Portale
    -0.52
    relle
    -0.46
    Im
    -0.46
     Im
    -0.46
    lib
    -0.45
    甚
    -0.45
    measures
    -0.44
     lib
    -0.44
    POSITIVE LOGITS
     Paglinawan
    0.69
     springfox
    0.62
     Италијани
    0.60
    __()
    0.59
    ()]
    
    0.59
    oa̍t
    0.59
     AssemblyCulture
    0.57
    ")){
    
    0.57
    RegressionTest
    0.57
    GHIJKLM
    0.56
    Activations Density 0.001%

    No Known Activations