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. 74430
    Prev
    Next
    INDEX
    Explanations

    rotary

    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
    примеча
    -0.58
    ViewFeatures
    -0.56
    enderror
    -0.55
    oster
    -0.52
    ExecutionContext
    -0.51
    IntoConstraints
    -0.51
    Clik
    -0.49
    رشف
    -0.49
    ArrowToggle
    -0.49
     RIG
    -0.48
    POSITIVE LOGITS
     li
    0.80
     bas
    0.75
     hath
    0.61
     ha
    0.61
     hag
    0.57
     hare
    0.57
    MigrationBuilder
    0.56
     baa
    0.55
     hai
    0.55
    bais
    0.55
    Activations Density 0.005%

    No Known Activations