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. 0-CLT-HP
    4. 40842
    Prev
    Next
    INDEX
    Explanations

    dark themes

    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
     giustizia
    -0.80
     zijne
    -0.76
     varandra
    -0.75
     vägen
    -0.75
     zelve
    -0.72
     martyrdom
    -0.70
     skolan
    -0.69
     įsi
    -0.69
     mijne
    -0.68
     fortfarande
    -0.67
    POSITIVE LOGITS
    er
    0.85
    ers
    0.84
    ette
    0.84
    ings
    0.82
    ations
    0.74
    able
    0.73
    ality
    0.73
    ian
    0.72
    aires
    0.71
    ous
    0.70
    Activations Density 0.518%

    No Known Activations