© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1040
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
    GEBURTSDATUM
    -0.80
    GenerationType
    -0.80
    ImageContext
    -0.77
    
    -0.73
    expandindo
    -0.73
     незавершена
    -0.72
    OGND
    -0.71
     BrowserModule
    -0.70
    Personensuche
    -0.70
    PropertyChanging
    -0.69
    POSITIVE LOGITS
     can
    1.24
     could
    1.10
    could
    0.75
     können
    0.73
    can
    0.71
     kunnen
    0.69
     peuvent
    0.67
     podemos
    0.66
     will
    0.66
     pouvez
    0.65
    Activations Density 0.003%

    No Known Activations