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. 12797
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and processes

    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
    <bos>
    -0.50
    帖最后由
    -0.49
    ServletConfig
    -0.49
     cerâmica
    -0.47
     cerámica
    -0.46
     stratég
    -0.45
    fromnode
    -0.44
     Ceinture
    -0.44
    Organizer
    -0.43
     låg
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.67
    AnchorStyles
    0.65
     patience
    0.64
     وتسجيلات
    0.63
    存于互联网档案馆
    0.60
    CodedInputStream
    0.59
    ционное
    0.58
     дописавши
    0.57
    netinet
    0.57
     works
    0.55
    Activations Density 0.030%

    No Known Activations