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. 22-CLT-HP
    4. 74515
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts

    np_max-act-logits · 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
    CPtr
    -0.56
    KURZBESCHREIBUNG
    -0.48
    Lop
    -0.45
    ́ng
    -0.43
    WEBPACK
    -0.43
     Changelog
    -0.43
    XMLSchema
    -0.43
     onCreate
    -0.43
    Parcelize
    -0.43
    untung
    -0.42
    POSITIVE LOGITS
    CodeAttribute
    0.60
     kasarigan
    0.58
    出版年
    0.58
    حياتها
    0.57
     "..\..\
    0.56
    professional
    0.53
    ilitary
    0.53
     professional
    0.53
    ">//
    0.52
     protoimpl
    0.51
    Activations Density 0.000%

    No Known Activations