© 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. 41990
    Prev
    Next
    INDEX
    Explanations

    IGF

    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
     resourceCulture
    -0.95
    WriteTagHelper
    -0.94
     Мексичка
    -0.90
    UnsafeEnabled
    -0.89
     useAppContext
    -0.87
    ReusableCell
    -0.87
     Exactos
    -0.84
    WebVitals
    -0.84
    DockStyle
    -0.84
    twimg
    -0.82
    POSITIVE LOGITS
    s
    0.71
    I
    0.55
    M
    0.54
    soft
    0.49
    S
    0.48
    ت
    0.44
    sa
    0.43
    ski
    0.43
    sb
    0.41
     Garland
    0.41
    Activations Density 0.076%

    No Known Activations