© 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. 5-CLT-HP
    7. 527
    Prev
    Next
    INDEX
    Explanations

    questions/requests

    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
     الحره
    -0.57
    AddHtmlAttribute
    -0.51
    styleUrls
    -0.50
    $.}
    -0.49
    $}
    -0.49
    Бахар
    -0.49
    {@
    -0.47
    ')):
    -0.47
    RunAsync
    -0.45
    )]:
    -0.45
    POSITIVE LOGITS
     Walkover
    0.59
    ?
    0.56
     يتيمه
    0.54
    izung
    0.54
    tvguidetime
    0.54
    nestjs
    0.51
    ropoda
    0.51
     esboço
    0.51
    ízo
    0.51
     EconPapers
    0.50
    Activations Density 0.041%

    No Known Activations