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. 74479
    Prev
    Next
    INDEX
    Explanations

    uncommon words and phrases

    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
    Aiheesta
    -0.63
    MigrationBuilder
    -0.60
     kasarigan
    -0.57
    expandindo
    -0.55
    帖最后由
    -0.54
     estekak
    -0.52
    /*---
    -0.52
     Geraadpleegd
    -0.51
    ########.
    -0.50
     mergeFrom
    -0.50
    POSITIVE LOGITS
     xlink
    0.56
    ChildScrollView
    0.56
    DispatchToProps
    0.54
    AndEndTag
    0.54
    onViewCreated
    0.51
    ActionCreators
    0.49
     onBind
    0.48
    enschutzer
    0.48
     AspNetCore
    0.48
     part
    0.47
    Activations Density 0.005%

    No Known Activations