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. 12925
    Prev
    Next
    INDEX
    Explanations

    will

    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
     للمعارف
    -1.03
     myſelf
    -1.02
     raiſ
    -1.02
     reaſon
    -0.97
     itſelf
    -0.97
     Jefus
    -0.97
    хьтан
    -0.96
     pleaſure
    -0.96
     cauſe
    -0.95
     GenerationType
    -0.94
    POSITIVE LOGITS
    SuccessListener
    0.42
     (
    0.41
     .
    0.41
     ask
    0.41
     use
    0.40
     test
    0.39
     if
    0.39
     the
    0.39
     as
    0.38
    ↵
    0.38
    Activations Density 0.035%

    No Known Activations