© 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. 1-CLT-HP
    7. 16197
    Prev
    Next
    INDEX
    Explanations

    focused

    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
    Negative Logits
    .
    -0.52
    <bos>
    -0.47
     focused
    -0.46
    ٬
    -0.44
    ,
    -0.44
    -
    -0.44
    Dedicated
    -0.43
    focused
    -0.43
     Dedicated
    -0.42
     ffilm
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.90
    RetentionPolicy
    0.88
    AddTagHelper
    0.87
     EconPapers
    0.77
    principalColumn
    0.73
     lenker
    0.73
    mybatisplus
    0.72
    YourGuide
    0.71
    thenReturn
    0.69
    RepeatedField
    0.67
    Activations Density 0.010%

    No Known Activations