© 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. 38265
    Prev
    Next
    INDEX
    Explanations

    Vegas

    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
    H
    -0.70
     H
    -0.70
    atrician
    -0.63
    unteer
    -0.57
    ing
    -0.55
    reciated
    -0.54
     Mile
    -0.53
    setH
    -0.53
    oporosis
    -0.52
    Traceback
    -0.50
    POSITIVE LOGITS
     protoimpl
    0.60
     AppModule
    0.59
    CodeAttribute
    0.59
    GraphicsUnit
    0.58
    XmlAccessType
    0.57
    IsContent
    0.53
    
    0.53
    EndProject
    0.53
     invokingState
    0.52
     resourceCulture
    0.50
    Activations Density 1.023%

    No Known Activations