© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2786
    Prev
    Next
    INDEX
    Explanations

    academic/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
    adaptiveStyles
    -0.75
     kasarigan
    -0.66
    ISupport
    -0.62
    ագրություններ
    -0.58
    BagLayout
    -0.57
    AnchorStyles
    -0.57
    <bos>
    -0.56
     Alde
    -0.55
    Referencie
    -0.54
    TagHelper
    -0.53
    POSITIVE LOGITS
     other
    0.65
     issues
    0.54
     وتسجيلات
    0.54
    ]--;
    0.53
    AddTagHelper
    0.52
     limited
    0.52
    ిక
    0.50
    こともある
    0.48
     the
    0.47
     growing
    0.47
    Activations Density 0.006%

    No Known Activations