© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13801
    Prev
    Next
    INDEX
    Explanations

    engine injection

    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
    <bos>
    -0.88
     propOrder
    -0.74
     springfox
    -0.65
     AssemblyTitle
    -0.63
     Numerade
    -0.60
     CreateTagHelper
    -0.60
     MainAxisSize
    -0.59
    ngdoc
    -0.57
    цезда
    -0.57
    webElementXpaths
    -0.55
    POSITIVE LOGITS
    NonQuery
    0.51
    databind
    0.51
    ankind
    0.50
    LabelTagHelper
    0.50
    ramide
    0.50
    徊
    0.49
     break
    0.49
    RetentionPolicy
    0.49
    wai
    0.49
    rodní
    0.48
    Activations Density 0.033%

    No Known Activations