© 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. 0-CLT-HP
    7. 94618
    Prev
    Next
    INDEX
    Explanations

    topes

    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
    haft
    -0.78
    que
    -0.66
    EDEFAULT
    -0.65
    zbęd
    -0.64
    .")
    -0.60
     IconData
    -0.60
     refusé
    -0.59
     détru
    -0.57
    elemField
    -0.57
    actively
    -0.56
    POSITIVE LOGITS
     []:
    0.56
    Mari
    0.56
    UnsafeEnabled
    0.49
     occupancy
    0.49
    pages
    0.48
    bole
    0.48
     Surgeon
    0.47
    ve
    0.47
    hou
    0.46
    vir
    0.46
    Activations Density 1.765%

    No Known Activations