© 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. 78129
    Prev
    Next
    INDEX
    Explanations

    Uncommon words/code

    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
    RegressionTest
    -0.54
    PROTOBUF
    -0.49
    NameInMap
    -0.49
    enumii
    -0.48
     adelante
    -0.45
    enumi
    -0.45
     sebagainya
    -0.44
    nocache
    -0.44
     joaat
    -0.43
     gyhoeddwyd
    -0.43
    POSITIVE LOGITS
     jsPsych
    0.62
     насељу
    0.62
    ']],
    0.58
    )}</
    0.56
    InvalidProtocol
    0.55
    SequentialGroup
    0.55
    ChromeDriver
    0.55
     Phry
    0.54
    migrationBuilder
    0.53
    hdfs
    0.52
    Activations Density 0.006%

    No Known Activations