© 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. 3022
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    GEBURTSDATUM
    -0.58
    Související
    -0.56
    devamını
    -0.55
     resourceCulture
    -0.52
     createSprite
    -0.50
     DriverManager
    -0.48
     fieldNum
    -0.47
    colgroup
    -0.47
    writeFieldEnd
    -0.47
    IntoConstraints
    -0.47
    POSITIVE LOGITS
     prevents
    0.79
     prohibits
    0.75
     gives
    0.75
     happens
    0.73
     makes
    0.73
    tagHelperRunner
    0.73
     eliminates
    0.71
     allows
    0.71
     helps
    0.70
     proves
    0.69
    Activations Density 0.001%

    No Known Activations