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. 22-CLT-HP
    4. 74260
    Prev
    Next
    INDEX
    Explanations

    Different languages/codes

    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
     dis
    -0.67
    UnsafeEnabled
    -0.65
     bad
    -0.63
     no
    -0.58
    binant
    -0.57
     CreateTagHelper
    -0.57
     stale
    -0.52
     wrongdoing
    -0.52
     disen
    -0.51
    IntoConstraints
    -0.51
    POSITIVE LOGITS
     विश्वसनीयता
    0.56
     alent
    0.56
    GraphicsUnit
    0.55
    ⓧ
    0.51
    fortawesome
    0.51
    COUVER
    0.50
     AssemblyTitle
    0.50
     Ellison
    0.49
     AppColors
    0.49
    QMetaType
    0.49
    Activations Density 0.004%

    No Known Activations