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. 11073
    Prev
    Next
    INDEX
    Explanations

    within

    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
    IntoConstraints
    -0.99
     يتيمه
    -0.98
    tagHelperRunner
    -0.94
     الحره
    -0.85
     AssemblyCulture
    -0.82
    InputBorder
    -0.82
    AutoScaleMode
    -0.78
     كومونز
    -0.77
    EndContext
    -0.76
    ViewFeatures
    -0.76
    POSITIVE LOGITS
    .
    0.71
     us
    0.57
     themselves
    0.56
    --;
    
    0.56
    们的
    0.54
     useRouter
    0.54
    ;
    0.52
    ative
    0.51
     ones
    0.50
    们
    0.49
    Activations Density 0.370%

    No Known Activations