© 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. 4-CLT-HP
    7. 1779
    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
     Baillargeon
    -0.91
    Gön
    -0.88
    IntoConstraints
    -0.79
    WebVitals
    -0.77
    Personendaten
    -0.75
    Rhestr
    -0.72
    saraba
    -0.71
    DockStyle
    -0.71
     ویکی‌پدیا
    -0.71
    יצוני
    -0.69
    POSITIVE LOGITS
    white
    0.66
     white
    0.64
    le
    0.55
     blancs
    0.51
     White
    0.51
     WHITE
    0.45
    White
    0.43
    unt
    0.42
    las
    0.41
    el
    0.41
    Activations Density 0.010%

    No Known Activations