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. 40910
    Prev
    Next
    INDEX
    Explanations

    non-profits and corporations

    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
     الحره
    -0.87
     Roskov
    -0.80
     cherchés
    -0.80
     feroit
    -0.79
     שוליים
    -0.79
    }],
    
    -0.76
     TextAppearance
    -0.75
    ISupport
    -0.75
    ंदीखरीदारी
    -0.75
     avoient
    -0.75
    POSITIVE LOGITS
    ist
    0.59
     community
    0.57
    base
    0.56
    ize
    0.54
    V
    0.54
    م
    0.53
    mas
    0.53
     mail
    0.53
    Mac
    0.53
    e
    0.53
    Activations Density 0.103%

    No Known Activations