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. 1-CLT-HP
    4. 11107
    Prev
    Next
    INDEX
    Explanations

    model

    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
     model
    -0.75
    новништво
    -0.67
    UIControlState
    -0.67
     Model
    -0.66
    Personensuche
    -0.65
    model
    -0.62
    MODEL
    -0.60
    DataAnnotations
    -0.59
    Model
    -0.57
     models
    -0.57
    POSITIVE LOGITS
    \{\\
    0.56
    structura
    0.54
     specifying
    0.52
    //{
    0.51
     cured
    0.51
     specification
    0.50
     vegetative
    0.49
     usefulness
    0.48
     '?
    0.48
    )}+
    0.48
    Activations Density 0.020%

    No Known Activations