© 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. 90910
    Prev
    Next
    INDEX
    Explanations

    QA and deficits

    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
     vPvB
    -0.80
    endphp
    -0.77
     تضيفلها
    -0.74
    parsedMessage
    -0.70
    ItemBackground
    -0.67
    tagHelperRunner
    -0.66
    InputTagHelper
    -0.66
    AsUp
    -0.65
     mapStateToProps
    -0.64
     mouseY
    -0.64
    POSITIVE LOGITS
    ing
    0.54
    ha
    0.49
     sembl
    0.49
    host
    0.47
    Host
    0.45
    uf
    0.44
    est
    0.43
    ul
    0.43
    ole
    0.43
     ועל
    0.42
    Activations Density 0.167%

    No Known Activations