© 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. 94417
    Prev
    Next
    INDEX
    Explanations

    secure

    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
     secure
    -1.15
     secured
    -1.08
     Secure
    -1.02
    secure
    -0.98
     securing
    -0.98
    Secure
    -0.94
     secures
    -0.94
    Secured
    -0.90
    secured
    -0.86
     option
    -0.82
    POSITIVE LOGITS
    er
    0.70
    fully
    0.66
    ly
    0.65
    st
    0.60
    arious
    0.57
    ed
    0.54
    ered
    0.54
    erden
    0.52
    ه
    0.52
    full
    0.52
    Activations Density 0.077%

    No Known Activations