© 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. 5-CLT-HP
    7. 97593
    Prev
    Next
    INDEX
    Explanations

    years

    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
     slightly
    -1.41
    slightly
    -1.34
     Slightly
    -1.30
    Slightly
    -1.27
     légèrement
    -1.16
     ligeramente
    -1.15
     leggermente
    -1.13
     nieco
    -1.04
     немного
    -1.03
     somewhat
    -1.00
    POSITIVE LOGITS
     '\\;'
    0.54
    BARA
    0.52
     drag
    0.50
     الرخصة
    0.49
    mstyle
    0.48
    UIControlState
    0.48
    '][]
    0.47
    bourg
    0.47
    ArrowToggle
    0.46
    -------------</
    0.46
    Activations Density 0.013%

    No Known Activations