© 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. 71562
    Prev
    Next
    INDEX
    Explanations

    Code, technical documents

    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
    ----</
    -0.75
    IUrlHelper
    -0.65
    kelijkheid
    -0.59
    UnitTesting
    -0.56
    зулта
    -0.54
    олові
    -0.52
    Hentet
    -0.52
    WithIOException
    -0.50
     cherchés
    -0.50
     heureuse
    -0.50
    POSITIVE LOGITS
    ParallelGroup
    0.72
    onAttach
    0.54
     completed
    0.52
    はじめに
    0.46
    telse
    0.44
     claimed
    0.43
    ecx
    0.42
    Réalisation
    0.41
    __*/
    0.41
    ])));
    0.41
    Activations Density 0.000%

    No Known Activations