© 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. 3-RES-MATRYOSHKA-DC
    7. 1906
    Prev
    Next
    INDEX
    Explanations

    the word "death"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Donaldson
    -0.58
     bubble
    -0.55
    OMO
    -0.54
     Trou
    -0.54
    лана
    -0.52
     problems
    -0.52
    ้อย
    -0.52
     Störungen
    -0.50
    扰
    -0.50
     pick
    -0.50
    POSITIVE LOGITS
     death
    2.83
     deaths
    2.53
    death
    2.50
     DEATH
    2.48
     Death
    2.45
    Death
    2.39
     died
    2.23
     Deaths
    2.23
    DEATH
    2.19
     muerte
    2.06
    Activations Density 0.391%

    No Known Activations