© 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. 0-CLT-HP
    7. 97054
    Prev
    Next
    INDEX
    Explanations

    {

    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
    uper
    -0.96
    ReusableCell
    -0.85
    SequentialGroup
    -0.71
     الحره
    -0.69
     MotionEvent
    -0.67
     समीक्षक
    -0.65
    parsedMessage
    -0.65
    windowFixed
    -0.62
    FundMe
    -0.60
    يميديا
    -0.58
    POSITIVE LOGITS
     nemlig
    0.49
     dafür
    0.47
    enumi
    0.46
     enf
    0.46
    enumii
    0.46
    charCodeAt
    0.46
     Tand
    0.45
    zeigt
    0.44
    rigos
    0.44
    λλην
    0.44
    Activations Density 0.129%

    No Known Activations