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. 0-CLT-HP
    4. 8
    Prev
    Next
    INDEX
    Explanations

    ces

    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
    ces
    -1.01
    s
    -0.60
     pre
    -0.55
     sound
    -0.55
     the
    -0.53
     
    -0.53
    ting
    -0.50
     p
    -0.50
     all
    -0.49
    cing
    -0.49
    POSITIVE LOGITS
    expandindo
    0.90
    RectangleBorder
    0.88
    WriteBarrier
    0.84
     שוליים
    0.81
     Roskov
    0.81
     newBuilder
    0.79
     متعلقه
    0.77
    NameInMap
    0.77
    Geplaatst
    0.77
     nahilalakip
    0.76
    Activations Density 0.110%

    No Known Activations