Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74504
    Prev
    Next
    INDEX
    Explanations

    abstract content

    np_max-act-logits · 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
    CloseOperation
    -0.59
    migrationBuilder
    -0.54
    instancetype
    -0.52
    adə
    -0.48
    faßt
    -0.48
    ünster
    -0.48
    énario
    -0.48
     mourir
    -0.46
     ivelany
    -0.46
    InstrumentedTest
    -0.45
    POSITIVE LOGITS
    Rujuakan
    0.56
     Wicidata
    0.56
    AndEndTag
    0.55
    汰
    0.54
     end
    0.53
    end
    0.51
     >=",
    0.51
     Nested
    0.50
    <bos>
    0.48
     autorytatywna
    0.48
    Activations Density 0.000%

    No Known Activations