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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96626
    Prev
    Next
    INDEX
    Explanations

    ases

    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
     transférez
    -0.61
    enterOuterAlt
    -0.51
     transfieras
    -0.49
    addFlags
    -0.49
     tslint
    -0.49
    ReusableCell
    -0.48
     ✭✭
    -0.47
    再加上
    -0.46
    styleUrls
    -0.46
    exitRule
    -0.46
    POSITIVE LOGITS
    tvguidetime
    0.85
     well
    0.59
    famous
    0.58
     famous
    0.56
    well
    0.52
    anadas
    0.50
     notoriously
    0.50
     unre
    0.49
     famously
    0.49
     Autorizaciones
    0.48
    Activations Density 0.001%

    No Known Activations