© 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. 357
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    panier
    -0.54
    Dh
    -0.48
    DeleteBehavior
    -0.47
     biologique
    -0.47
    
    -0.46
     régulière
    -0.46
     sonore
    -0.45
     "¿
    -0.45
    pump
    -0.44
    Salta
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.59
    protoimpl
    0.58
     يتيمه
    0.55
     tradition
    0.54
     aidant
    0.54
    multicolumn
    0.54
    ніципалі
    0.53
     responsibility
    0.52
    Personensuche
    0.52
    ApiOperation
    0.52
    Activations Density 0.002%

    No Known Activations