© 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. 0-CLT-HP
    7. 92304
    Prev
    Next
    INDEX
    Explanations

    checkout

    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
     checkout
    -0.99
     Checkout
    -0.84
     Cheney
    -0.75
     Tras
    -0.74
    checkout
    -0.74
    agger
    -0.72
    Checkout
    -0.63
    Tras
    -0.62
    AppBar
    -0.60
     Вікі
    -0.60
    POSITIVE LOGITS
    
    0.63
    Portale
    0.56
    Handlung
    0.54
    +#+#
    0.53
     TCS
    0.53
    extAlignment
    0.52
     AssemblyProduct
    0.51
     cherchés
    0.49
     Thon
    0.49
    ########.
    0.48
    Activations Density 2.086%

    No Known Activations