© 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. 5-CLT-HP
    7. 6135
    Prev
    Next
    INDEX
    Explanations

    with

    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
    '}';
    -0.47
    anceled
    -0.44
     parla
    -0.38
    dena
    -0.38
    älfte
    -0.37
    */),
    -0.36
    ErrUnexpectedEOF
    -0.36
     gili
    -0.36
    celo
    -0.35
    <bos>
    -0.35
    POSITIVE LOGITS
     مشين
    0.79
    sizeCache
    0.77
    istoitu
    0.73
    mybatisplus
    0.72
    AddTagHelper
    0.67
    virons
    0.67
     henvisninger
    0.62
    ValueGeneration
    0.62
    arraycopy
    0.62
     MainAxisSize
    0.61
    Activations Density 0.003%

    No Known Activations