© 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. 1-CLT-HP
    4. 45847
    Prev
    Next
    INDEX
    Explanations

    ground

    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
     ground
    -1.02
     Ground
    -0.87
    ground
    -0.85
    GROUND
    -0.81
    Ground
    -0.78
     GROUND
    -0.77
     grounds
    -0.55
    Vanjske
    -0.51
     grond
    -0.49
     floor
    -0.48
    POSITIVE LOGITS
    expandindo
    0.92
    WriteBarrier
    0.86
     esternos
    0.75
    تقاوى
    0.71
    JspWriter
    0.69
    tagHelperRunner
    0.68
    EndContext
    0.67
    Хьажоргаш
    0.66
     nahilalakip
    0.65
    aarrggbb
    0.64
    Activations Density 0.024%

    No Known Activations