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. 0-CLT-HP
    4. 40805
    Prev
    Next
    INDEX
    Explanations

    on

    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
    layui
    -0.59
     or
    -0.55
     useParams
    -0.51
    ViewChild
    -0.50
    UserScript
    -0.49
    createTable
    -0.49
    ValueStyle
    -0.48
     against
    -0.48
    addCriterion
    -0.46
     bedro
    -0.45
    POSITIVE LOGITS
    <bos>
    0.63
    a
    0.57
     ProtoMessage
    0.56
     a
    0.53
    pouring
    0.53
    e
    0.53
    Especially
    0.52
     ExecuteAsync
    0.52
    Later
    0.52
    })));
    0.51
    Activations Density 0.027%

    No Known Activations