© 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. 5-CLT-HP
    7. 506
    Prev
    Next
    INDEX
    Explanations

    locations/states

    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
     GenerationType
    -0.57
    jsonwebtoken
    -0.50
     Baillargeon
    -0.50
    IBOutlet
    -0.47
     Terminals
    -0.46
     téléphonique
    -0.45
     бр
    -0.45
    OrNil
    -0.45
     suitcases
    -0.43
    nofollow
    -0.43
    POSITIVE LOGITS
     attes
    0.52
    expandindo
    0.51
    duc
    0.49
     peores
    0.49
    run
    0.49
    deinit
    0.48
    डी
    0.48
    Run
    0.48
    fjspx
    0.47
     estimés
    0.47
    Activations Density 0.002%

    No Known Activations