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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91630
    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
    edig
    -0.67
    aire
    -0.59
    AlterField
    -0.57
    eer
    -0.52
    atina
    -0.52
    aita
    -0.50
    aster
    -0.50
    olia
    -0.50
    etes
    -0.49
    atric
    -0.48
    POSITIVE LOGITS
    WireFormatLite
    0.65
    ArrowToggle
    0.63
    PerformLayout
    0.62
    AndEndTag
    0.62
    enumii
    0.60
    
    0.59
    AddTagHelper
    0.58
    UrlResolution
    0.57
     Мексичка
    0.55
    findpost
    0.55
    Activations Density 0.001%

    No Known Activations