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. 74533
    Prev
    Next
    INDEX
    Explanations

    mammals

    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
     Italijanski
    -0.67
     Pitman
    -0.51
    WebElementEntity
    -0.51
    NewUrlParser
    -0.51
    utnik
    -0.51
     Paglinawan
    -0.49
    ThroughAttribute
    -0.48
     CURIAM
    -0.47
     Blackstone
    -0.47
    {§
    -0.47
    POSITIVE LOGITS
     AssemblyProduct
    0.64
    ISupport
    0.58
     forge
    0.57
     iconLine
    0.56
    Спољашње
    0.56
    ynb
    0.55
     cref
    0.55
     OMIT
    0.54
     <<<<<<<<<<<<<<
    0.54
    forge
    0.54
    Activations Density 0.001%

    No Known Activations