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. 11156
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific Texts

    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
     coû
    -0.56
    发表于
    -0.52
    ystemet
    -0.52
     souple
    -0.52
    wpi
    -0.50
    Portale
    -0.49
    WithIOException
    -0.48
    udh
    -0.47
    ztály
    -0.47
    olyte
    -0.47
    POSITIVE LOGITS
    ंदीखरीदारी
    0.65
    s
    0.57
     Tira
    0.52
    MLLoader
    0.52
     vore
    0.51
    chengladbach
    0.51
     chande
    0.51
    SaveVideo
    0.49
     viewHolder
    0.48
     gratific
    0.47
    Activations Density 0.557%

    No Known Activations