© 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. 4-CLT-HP
    7. 602
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     >=",
    -0.49
    SizeF
    -0.49
    Abit
    -0.48
     ModelExpression
    -0.47
     [{
    -0.46
    Registered
    -0.45
    ffine
    -0.45
    )_/¯
    -0.45
    urlpatterns
    -0.45
    exitRule
    -0.45
    POSITIVE LOGITS
     AssemblyCompany
    0.49
     Book
    0.49
    ApplicationTests
    0.47
    BeginContext
    0.46
    CardBody
    0.44
     Day
    0.44
    });*/
    0.43
     Standard
    0.42
    })*/
    0.42
     Y
    0.41
    Activations Density 0.008%

    No Known Activations