© 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. 3791
    Prev
    Next
    INDEX
    Explanations

    the

    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
     defaultstate
    -0.50
     esprits
    -0.50
    ngrx
    -0.50
     enjeux
    -0.49
    DataAnnotations
    -0.49
     spéciales
    -0.48
     laterales
    -0.48
    simpleType
    -0.47
    GenerationType
    -0.46
     chré
    -0.46
    POSITIVE LOGITS
     growing
    0.67
     saites
    0.59
     Growing
    0.57
     increasing
    0.57
     rapidly
    0.56
     ever
    0.56
    growing
    0.55
     professors
    0.55
     InputDecoration
    0.54
     bezeichneter
    0.53
    Activations Density 0.001%

    No Known Activations