© 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. 513
    Prev
    Next
    INDEX
    Explanations

    environmental issues

    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
    <bos>
    -0.69
    cabe
    -0.59
    }")]
    -0.59
    inale
    -0.58
     ujednoznacz
    -0.57
    //
    -0.53
     facie
    -0.52
     colorear
    -0.49
     säl
    -0.48
     kveld
    -0.48
    POSITIVE LOGITS
    arraycopy
    0.56
     تانيه
    0.52
     resourceCulture
    0.52
     environmental
    0.51
    addContainerGap
    0.51
     AssemblyProduct
    0.50
     simultaneously
    0.50
    ArgumentParser
    0.49
    ailleurs
    0.47
    gridx
    0.46
    Activations Density 0.002%

    No Known Activations