© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41206
    Prev
    Next
    INDEX
    Explanations

    side, step

    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
    ÍTULO
    -0.57
    ftance
    -0.55
    źródło
    -0.51
    Давайте
    -0.51
    rões
    -0.50
    씩
    -0.50
    ADORA
    -0.49
    sterious
    -0.47
    StateException
    -0.47
    corazón
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.75
     propOrder
    0.68
    webElementXpaths
    0.68
    ItemBackground
    0.67
    awtextra
    0.65
     <<<<<<<<<<<<<<
    0.62
    
    0.62
    abestanden
    0.62
    SequentialGroup
    0.61
    出版年
    0.60
    Activations Density 0.023%

    No Known Activations