© 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. 1-CLT-HP
    7. 9334
    Prev
    Next
    INDEX
    Explanations

    expected

    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
    expected
    -0.94
     expected
    -0.88
    expect
    -0.80
     Expected
    -0.79
    Expected
    -0.76
    Expect
    -0.75
     expect
    -0.75
     Expect
    -0.72
     EXPECT
    -0.71
    EXPECTED
    -0.65
    POSITIVE LOGITS
     to
    0.71
    baomidou
    0.64
     AssemblyCulture
    0.60
    uate
    0.55
     later
    0.55
    <bos>
    0.54
     мәкал
    0.54
    uality
    0.52
    autaire
    0.52
    oa̍t
    0.52
    Activations Density 0.015%

    No Known Activations