© 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. 5-CLT-HP
    7. 5129
    Prev
    Next
    INDEX
    Explanations

    living/alive

    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
     survive
    -1.04
     survival
    -1.04
     survives
    -1.00
     Survival
    -0.97
    survival
    -0.96
     surviving
    -0.95
     Survi
    -0.94
    survi
    -0.94
     Survive
    -0.93
     sobrevivir
    -0.92
    POSITIVE LOGITS
     كومونز
    0.66
     Efq
    0.56
    OGND
    0.55
     onCancelled
    0.55
     Wikimedijinoj
    0.53
     Că
    0.53
     esternos
    0.53
    Искәрмәләр
    0.52
     Neander
    0.52
     Shakspeare
    0.51
    Activations Density 0.005%

    No Known Activations