© 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. 5-CLT-HP
    7. 94991
    Prev
    Next
    INDEX
    Explanations

    previously

    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
     оригіналу
    -0.58
     Commencez
    -0.52
    GEBURTSDATUM
    -0.51
    else
    -0.50
    letzt
    -0.49
     елның
    -0.49
    原来
    -0.49
     Wants
    -0.48
    NUMX
    -0.48
    ValueGenerated
    -0.48
    POSITIVE LOGITS
     not
    0.78
     only
    0.71
     never
    0.60
     didn
    0.59
     relied
    0.59
     onely
    0.59
     ſee
    0.58
     may
    0.56
     '\\;'
    0.56
     didnt
    0.56
    Activations Density 0.004%

    No Known Activations