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. 20-CLT-HP
    4. 74026
    Prev
    Next
    INDEX
    Explanations

    dp

    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
     CURLOPT
    -0.57
    WriteLiteral
    -0.54
    styleType
    -0.53
     máximo
    -0.49
    arga
    -0.48
    qrstuvwxyz
    -0.48
     poveznice
    -0.48
    opan
    -0.48
     Bundle
    -0.47
    ########.
    -0.47
    POSITIVE LOGITS
    UIControlState
    0.68
    SourceChecksum
    0.60
     AppColors
    0.60
     stanovnika
    0.60
     TextEditing
    0.59
    SpringBootTest
    0.57
     onCancelled
    0.55
    ArrowToggle
    0.55
     Monfieur
    0.54
     ſur
    0.54
    Activations Density 0.000%

    No Known Activations