© 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. 0-CLT-HP
    7. 45061
    Prev
    Next
    INDEX
    Explanations

    upon

    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
     upon
    -1.22
    upon
    -0.99
    Upon
    -0.92
     UPON
    -0.85
     Upon
    -0.84
    ValueStyle
    -0.60
     näm
    -0.56
     nemlig
    -0.56
    Datuak
    -0.55
     hjälp
    -0.54
    POSITIVE LOGITS
     Efq
    0.74
     Jefus
    0.70
     Majefty
    0.69
     Diſ
    0.69
     the
    0.64
     intermittent
    0.62
     pleaſure
    0.62
     Monfieur
    0.61
     Theſe
    0.60
     digital
    0.59
    Activations Density 0.049%

    No Known Activations