© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 41082
    Prev
    Next
    INDEX
    Explanations

    gr

    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
     using
    -1.10
     Using
    -1.07
     utilizando
    -1.07
    Using
    -0.99
     USING
    -0.99
    using
    -0.95
     utilizzando
    -0.94
     menggunakan
    -0.92
     usando
    -0.91
     folos
    -0.82
    POSITIVE LOGITS
     desorption
    0.66
     synap
    0.64
     dysplasia
    0.63
     pyrolysis
    0.62
     perox
    0.61
     compressors
    0.60
     Conductivity
    0.60
     autoradio
    0.60
     Penetration
    0.60
     piezoelectric
    0.59
    Activations Density 0.045%

    No Known Activations