© 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. 5-CLT-HP
    4. 96392
    Prev
    Next
    INDEX
    Explanations

    Code and technical discussions

    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
     it
    -0.79
     that
    -0.74
     how
    -0.69
     why
    -0.67
     we
    -0.58
     what
    -0.57
     It
    -0.56
     these
    -0.52
     completely
    -0.50
     These
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.89
    CppMethod
    0.85
    zzleHttp
    0.79
     Paglinawan
    0.77
     offroad
    0.73
    THISDAY
    0.72
     Matériau
    0.70
     AllAfrica
    0.69
     betweenstory
    0.65
     Leland
    0.63
    Activations Density 0.000%

    No Known Activations