© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71420
    Prev
    Next
    INDEX
    Explanations

    Unstructured/random data

    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
    Negative Logits
     wireType
    -0.57
    webElementGuid
    -0.56
    interopRequire
    -0.54
    ⓧ
    -0.51
     premia
    -0.51
     Vikipedi
    -0.50
     Jeune
    -0.48
    ★★★★☆
    -0.47
    期刊论文
    -0.47
    NewUrlParser
    -0.47
    POSITIVE LOGITS
    Slf
    0.60
    numerusform
    0.54
     Gode
    0.53
     useSelector
    0.50
     noqa
    0.50
     PartialEq
    0.50
    >{@
    0.48
    merkung
    0.47
     <>",
    0.46
     EconPapers
    0.46
    Activations Density 0.000%

    No Known Activations