© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    on

    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
    NOPQRST
    -0.44
    AnimationsModule
    -0.43
     resultCode
    -0.42
    WebVitals
    -0.42
     MainAxisSize
    -0.41
    withstanding
    -0.39
     BitmapFactory
    -0.38
    대로
    -0.37
    .*")]
    -0.35
    PageIndex
    -0.35
    POSITIVE LOGITS
    port
    0.63
    placed
    0.59
    tro
    0.59
    bro
    0.57
    aus
    0.56
    ंदीखरीदारी
    0.56
    told
    0.56
    yp
    0.56
    por
    0.55
    gn
    0.54
    Activations Density 0.002%

    No Known Activations