© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94193
    Prev
    Next
    INDEX
    Explanations

    upgrade

    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
    Not in Any Lists

    No Comments

    Negative Logits
     affaires
    -0.59
     prestazioni
    -0.57
     assic
    -0.56
     contextLoads
    -0.53
     perspective
    -0.53
    er
    -0.52
     flesta
    -0.52
     églises
    -0.52
     servicing
    -0.50
     biens
    -0.50
    POSITIVE LOGITS
     Roskov
    0.81
     SwitchCompat
    0.78
     ExecuteAsync
    0.73
     '\\;'
    0.73
     autorytatywna
    0.72
     مشين
    0.70
    Handlung
    0.70
    :+:
    0.66
    CloseOperation
    0.64
     LoggerFactory
    0.63
    Activations Density 1.567%

    No Known Activations