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. 1-CLT-HP
    4. 11214
    Prev
    Next
    INDEX
    Explanations

    public

    np_max-act · 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
     propOrder
    -0.78
     Normdatei
    -0.74
    Билгалдахарш
    -0.69
    ConstraintMaker
    -0.62
     تانيه
    -0.57
    ItemGroup
    -0.57
    makeConstraints
    -0.56
    WarningLevel
    -0.56
    RegressionTest
    -0.56
    strSql
    -0.56
    POSITIVE LOGITS
    enderror
    0.51
    MemoryWarning
    0.46
    gadas
    0.44
     endwhile
    0.44
    abetes
    0.44
    nought
    0.43
    anci
    0.43
     packageName
    0.41
     chóng
    0.41
     GONE
    0.41
    Activations Density 0.163%

    No Known Activations