© 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. 9044
    Prev
    Next
    INDEX
    Explanations

    authentication

    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
     authenticity
    -1.76
     Authenticity
    -1.41
    authentic
    -1.02
    Authentic
    -0.97
     authentic
    -0.94
     Authentic
    -0.77
     autentic
    -0.76
     genu
    -0.76
     authenti
    -0.73
     originality
    -0.73
    POSITIVE LOGITS
     toallas
    0.48
     devons
    0.47
     travailleurs
    0.47
    sieme
    0.47
     abstrait
    0.46
     milliers
    0.46
     huiles
    0.45
     crainte
    0.45
     vétérina
    0.45
     courants
    0.44
    Activations Density 0.011%

    No Known Activations