© 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. 0-CLT-HP
    4. 90764
    Prev
    Next
    INDEX
    Explanations

    big

    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
     big
    -1.20
    big
    -0.93
    ChildScrollView
    -0.88
     Big
    -0.80
    Big
    -0.79
    OGND
    -0.77
     BIG
    -0.76
    Rüyada
    -0.76
    BIG
    -0.73
    RenderAtEndOf
    -0.70
    POSITIVE LOGITS
    oted
    0.80
    ,
    0.53
    arithmic
    0.52
    shots
    0.51
     and
    0.50
    igned
    0.48
    titutions
    0.48
    gered
    0.47
    shot
    0.46
    -
    0.46
    Activations Density 0.020%

    No Known Activations