© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97064
    Prev
    Next
    INDEX
    Explanations

    continuation or persistence

    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
    InjectAttribute
    -0.71
    
    -0.69
    Diweddarwch
    -0.69
    protoimpl
    -0.67
    ParallelGroup
    -0.64
     NSCoder
    -0.63
    EndProject
    -0.63
     continúas
    -0.62
    ImageContext
    -0.60
    UnknownFields
    -0.58
    POSITIVE LOGITS
     to
    0.60
    piratory
    0.47
     an
    0.46
    meck
    0.46
     one
    0.45
     estimés
    0.45
    liferation
    0.44
     mergeFrom
    0.44
    printStackTrace
    0.43
     Dou
    0.42
    Activations Density 0.003%

    No Known Activations