© 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. 5-CLT-HP
    4. 3176
    Prev
    Next
    INDEX
    Explanations

    lifts

    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
     Then
    -0.73
    Then
    -0.72
     then
    -0.71
     sitten
    -0.70
    then
    -0.58
     потом
    -0.57
     THEN
    -0.54
     vervolgens
    -0.54
    再去
    -0.53
     dann
    -0.51
    POSITIVE LOGITS
     NSCoder
    0.89
    __(/*!
    0.88
    ſelves
    0.84
    etheless
    0.83
    __":
    0.82
     initComponents
    0.82
     Мексичка
    0.82
     useAppContext
    0.81
    principalColumn
    0.81
    ReusableCell
    0.80
    Activations Density 0.147%

    No Known Activations