© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4529
    Prev
    Next
    INDEX
    Explanations

    location

    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
     detalj
    -0.48
     geleverd
    -0.44
     alguno
    -0.42
    UMNS
    -0.42
     toege
    -0.40
    itates
    -0.39
     Membuat
    -0.39
    gnation
    -0.38
    cibles
    -0.38
    lierte
    -0.37
    POSITIVE LOGITS
    Portail
    0.79
     network
    0.70
     newOwner
    0.69
     Вікі
    0.68
     SafeMath
    0.65
    UnsafeEnabled
    0.63
     implications
    0.63
     Meksiku
    0.62
     reach
    0.61
     results
    0.60
    Activations Density 0.003%

    No Known Activations