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. 74529
    Prev
    Next
    INDEX
    Explanations

    put

    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
     defaultstate
    -0.57
    SequentialGroup
    -0.55
    RegistryLite
    -0.51
     wal
    -0.51
     WebApplication
    -0.50
     Dafür
    -0.49
     /\.(
    -0.49
     PartialEq
    -0.47
     estekak
    -0.47
    IsMutable
    -0.47
    POSITIVE LOGITS
    addHandler
    0.52
     réserver
    0.51
    des
    0.51
    ades
    0.50
     Sousa
    0.49
    ynx
    0.49
    nová
    0.48
     récompenses
    0.48
    حوالہ
    0.48
    ennies
    0.48
    Activations Density 0.011%

    No Known Activations