© 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. 1556
    Prev
    Next
    INDEX
    Explanations

    programming code, includes

    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
     
    -0.62
    WebElementEntity
    -0.54
    prnewswire
    -0.51
     material
    -0.49
     ho
    -0.48
    AfterClass
    -0.48
    ValueStyle
    -0.48
    BeforeMethod
    -0.47
     hu
    -0.46
     star
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.71
     صوتيه
    0.61
     مشين
    0.60
    LayoutStyle
    0.59
    LError
    0.56
     Affiliations
    0.55
    RegressionTest
    0.54
     rhetor
    0.54
     underscored
    0.54
     oars
    0.53
    Activations Density 1.876%

    No Known Activations