© 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. 78194
    Prev
    Next
    INDEX
    Explanations

    were

    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
     simultaneously
    -1.83
     at
    -1.74
     Simultaneously
    -1.56
    simult
    -1.52
     gleichzeitig
    -1.52
     одновременно
    -1.50
     jednocześnie
    -1.50
     concurrently
    -1.40
    same
    -1.35
    Simult
    -1.35
    POSITIVE LOGITS
    ToTensor
    0.54
    mtrl
    0.54
    СТВ
    0.53
    AsUp
    0.52
    følgelig
    0.52
    DetailComponent
    0.51
     فريبيس
    0.50
     saja
    0.50
    openConnection
    0.50
    ](#
    0.50
    Activations Density 0.000%

    No Known Activations