© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15366
    Prev
    Next
    INDEX
    Explanations

    skepticism

    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
     skepticism
    -1.00
     sceptical
    -0.98
     skeptical
    -0.94
     scepticism
    -0.90
    ArrowToggle
    -0.83
    psy
    -0.82
     يتيمه
    -0.77
    expandindo
    -0.74
     skep
    -0.71
    Autoritní
    -0.68
    POSITIVE LOGITS
     of
    0.52
    glDelete
    0.48
    cmath
    0.48
     tế
    0.46
    ミュ
    0.43
    d
    0.43
    metter
    0.42
    オブ
    0.42
    แล้ว
    0.41
    dry
    0.40
    Activations Density 0.169%

    No Known Activations