© 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. 0-CLT-HP
    7. 90713
    Prev
    Next
    INDEX
    Explanations

    indo

    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
    substack
    -0.57
     CreateTagHelper
    -0.50
     gypsum
    -0.48
    URLException
    -0.47
    oraus
    -0.46
    eser
    -0.46
     <=",
    -0.46
    ⓧ
    -0.45
    :][
    -0.45
     Gour
    -0.45
    POSITIVE LOGITS
    nish
    0.60
     sogni
    0.58
     engraçadas
    0.57
    ltä
    0.57
     الحره
    0.57
    ppuden
    0.55
    WebElementEntity
    0.54
    mapStateToProps
    0.53
    UGS
    0.53
     umana
    0.53
    Activations Density 0.566%

    No Known Activations