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. 11284
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    MigrationBuilder
    -1.23
    TagHelper
    -0.86
    IntoConstraints
    -0.81
    CloseOperation
    -0.81
     NUKAT
    -0.79
     betweenstory
    -0.78
    سطس
    -0.77
     Roskov
    -0.75
    tvguidetime
    -0.75
     InputDecoration
    -0.75
    POSITIVE LOGITS
     of
    0.53
    Cap
    0.46
    .
    0.45
     liel
    0.42
    Port
    0.42
    Post
    0.41
     Verhältnis
    0.40
     Rapid
    0.40
     in
    0.39
    key
    0.39
    Activations Density 0.800%

    No Known Activations