© 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. 0-CLT-HP
    7. 38381
    Prev
    Next
    INDEX
    Explanations

    but

    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
     beginnetje
    -0.85
    sizeCache
    -0.71
     ferdig
    -0.70
     Roskov
    -0.68
     nødvendig
    -0.67
     تضيفلها
    -0.64
     hendes
    -0.63
     ám
    -0.63
     pero
    -0.61
     professeurs
    -0.60
    POSITIVE LOGITS
    tom
    0.50
    ane
    0.48
     since
    0.48
    Slf
    0.46
    urig
    0.46
    FontOfSize
    0.45
    ting
    0.45
    setPointSize
    0.45
     VMs
    0.45
     router
    0.44
    Activations Density 0.149%

    No Known Activations