© 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. 43353
    Prev
    Next
    INDEX
    Explanations

    damaged or detected

    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
     detected
    -1.16
     destroyed
    -1.12
     détru
    -1.07
     Detected
    -1.05
     damaged
    -0.99
    detected
    -0.98
     Damaged
    -0.94
     identified
    -0.93
     détect
    -0.92
    httphttps
    -0.92
    POSITIVE LOGITS
     by
    0.75
     the
    0.65
    AccessorTable
    0.57
     as
    0.56
     and
    0.55
     a
    0.54
     further
    0.49
     memory
    0.49
     in
    0.49
     international
    0.47
    Activations Density 0.083%

    No Known Activations