© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91766
    Prev
    Next
    INDEX
    Explanations

    code or copyright text

    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
     חיצוניים
    -0.61
     AssemblyTitle
    -0.60
     مرئيه
    -0.60
    RegressionTest
    -0.59
    AnchorTagHelper
    -0.59
    thâu
    -0.58
     ComVisible
    -0.58
    nonatomic
    -0.57
     Meksiku
    -0.57
    Geplaatst
    -0.56
    POSITIVE LOGITS
     prefent
    0.57
     eve
    0.55
    HtmlAttribute
    0.50
     alpina
    0.50
     šal
    0.49
    المناصب
    0.49
     fhort
    0.49
     Latham
    0.49
    зно
    0.49
     Whistler
    0.48
    Activations Density 0.003%

    No Known Activations