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. 11248
    Prev
    Next
    INDEX
    Explanations

    jazz

    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
    abestanden
    -0.75
     jsPsych
    -0.74
    MigrationBuilder
    -0.72
    Kaynakça
    -0.69
    oretical
    -0.68
     Exodus
    -0.66
     &___
    -0.65
    ysaccharides
    -0.63
    hetics
    -0.63
    apolis
    -0.61
    POSITIVE LOGITS
     Sicht
    0.41
     rest
    0.40
     choice
    0.40
     confidence
    0.39
    Masukkan
    0.39
    ükü
    0.38
    Pilih
    0.38
    IgnoreCase
    0.37
     belief
    0.36
     strategically
    0.36
    Activations Density 0.012%

    No Known Activations