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. 20-CLT-HP
    4. 74076
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
    matchCondition
    -0.48
    findElement
    -0.43
    usalem
    -0.42
     Auff
    -0.41
     ricordare
    -0.40
    amesh
    -0.40
     ocurrió
    -0.40
     évaluation
    -0.39
     Low
    -0.39
     O
    -0.39
    POSITIVE LOGITS
    TagMode
    0.90
     AssemblyCulture
    0.85
     typelib
    0.78
    ]));
    
    0.73
    PerformLayout
    0.73
     ***!
    0.73
    nodoc
    0.72
     незавершена
    0.70
    脚注の使い方
    0.69
    ScopeManager
    0.68
    Activations Density 0.013%

    No Known Activations