© 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. 20-CLT-HP
    7. 76448
    Prev
    Next
    INDEX
    Explanations

    safe

    np_max-act-logits · 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
     onCancelled
    -0.62
    contentLoaded
    -0.57
    writeField
    -0.56
    ietic
    -0.56
    ghed
    -0.50
     aDecoder
    -0.50
    roidered
    -0.49
     întâ
    -0.49
    DataSetChanged
    -0.48
     viewType
    -0.48
    POSITIVE LOGITS
     SAFE
    0.57
     safe
    0.52
     Safe
    0.49
    ziplin
    0.49
    Safe
    0.48
    ########.
    0.47
     Pace
    0.47
     safeguard
    0.47
     to
    0.46
     Safety
    0.46
    Activations Density 0.000%

    No Known Activations