© 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. 97451
    Prev
    Next
    INDEX
    Explanations

    your

    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
     initComponents
    -0.73
     femininas
    -0.71
     cherchés
    -0.65
     ivelany
    -0.61
    İstinadlar
    -0.60
    IUrlHelper
    -0.58
     Efq
    -0.57
     gynhyrchwyd
    -0.57
    Tikang
    -0.57
     pitié
    -0.56
    POSITIVE LOGITS
     tales
    1.27
     tale
    1.15
     stories
    1.02
    tales
    0.95
     Tales
    0.94
    Tales
    0.91
     story
    0.86
    tale
    0.83
     narratives
    0.81
    Tale
    0.79
    Activations Density 0.012%

    No Known Activations