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. 12930
    Prev
    Next
    INDEX
    Explanations

    commonality and possibilities

    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
    GEBURTSDATUM
    -0.63
     CreateTagHelper
    -0.62
     Réponses
    -0.59
    WithIOException
    -0.58
     mergeFrom
    -0.57
    AnchorTagHelper
    -0.57
     transfieras
    -0.55
    oredCriteria
    -0.54
     OMITTED
    -0.52
    出版年
    -0.52
    POSITIVE LOGITS
     with
    0.68
    <bos>
    0.63
     in
    0.56
     by
    0.56
     NavController
    0.54
     configureStore
    0.54
     when
    0.52
     about
    0.50
     contextLoads
    0.50
    dropna
    0.49
    Activations Density 0.695%

    No Known Activations