© 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. 20-CLT-HP
    4. 74785
    Prev
    Next
    INDEX
    Explanations

    code imports and snippets

    np_max-act-logits · 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
    webElementXpaths
    -0.90
    RegressionTest
    -0.86
    EDEFAULT
    -0.80
    oa̍t
    -0.79
     kaarangay
    -0.75
     estekak
    -0.75
    sidemargin
    -0.73
    SBATCH
    -0.72
    Lower
    -0.69
     betweenstory
    -0.69
    POSITIVE LOGITS
     forward
    0.64
     back
    0.59
     ahead
    0.52
     front
    0.44
     bak
    0.41
     forwards
    0.40
    iran
    0.38
     впер
    0.38
     hậu
    0.36
    Cursors
    0.36
    Activations Density 0.001%

    No Known Activations