© 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. 4-CLT-HP
    7. 3041
    Prev
    Next
    INDEX
    Explanations

    must

    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
    PreferredItem
    -0.71
    RegressionTest
    -0.70
    terase
    -0.69
     كومونز
    -0.68
    viewDidLoad
    -0.68
    MLLoader
    -0.65
     egos
    -0.62
     pinulongan
    -0.61
     ResponseEntity
    -0.61
    Portail
    -0.61
    POSITIVE LOGITS
    HideFlags
    0.53
     történ
    0.50
     presentarse
    0.50
     aggi
    0.49
     fit
    0.49
     occur
    0.49
     result
    0.48
     CreateTagHelper
    0.48
     happen
    0.47
     betra
    0.47
    Activations Density 0.008%

    No Known Activations