Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74279
    Prev
    Next
    INDEX
    Explanations

    Explaining

    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
    ImageContext
    -0.72
    IBarButtonItem
    -0.65
    Rüyada
    -0.65
    consistency
    -0.63
    ❮
    -0.60
    erequisite
    -0.59
    ArgsConstructor
    -0.58
    niająca
    -0.58
    language
    -0.57
    bootstrapcdn
    -0.57
    POSITIVE LOGITS
     express
    0.49
     clearly
    0.43
     explain
    0.43
    imu
    0.42
     open
    0.42
     fit
    0.42
     tell
    0.42
     describe
    0.41
     recorded
    0.41
     Explain
    0.40
    Activations Density 0.000%

    No Known Activations