© 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. 1-CLT-HP
    7. 722
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    inerja
    -0.54
     
    -0.53
    Autoritní
    -0.50
    SceneManagement
    -0.48
    FormTagHelper
    -0.48
    balanceOf
    -0.47
    Šaltiniai
    -0.47
    SupportActionBar
    -0.47
     ſeveral
    -0.46
     asymptomatic
    -0.46
    POSITIVE LOGITS
    ly
    0.65
    :
    0.62
    ness
    0.62
    ami
    0.61
    tho
    0.61
    itoba
    0.61
    ity
    0.60
    ,
    0.60
    ials
    0.58
    izations
    0.58
    Activations Density 0.061%

    No Known Activations