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. 11044
    Prev
    Next
    INDEX
    Explanations

    cells

    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
    NameInMap
    -1.04
    EndInit
    -0.87
     linkovi
    -0.84
    +#+#
    -0.82
     HasFactory
    -0.81
     propOrder
    -0.78
     GenerationType
    -0.77
    WebElementEntity
    -0.77
     jScrollPane
    -0.77
    Попис
    -0.77
    POSITIVE LOGITS
     recovered
    0.55
     recruited
    0.47
     from
    0.47
     enrolled
    0.47
     called
    0.46
     dealt
    0.45
     driving
    0.45
     dealing
    0.44
     secret
    0.44
     served
    0.43
    Activations Density 0.118%

    No Known Activations