© 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. 24-RES-MATRYOSHKA-DC
    7. 957
    Prev
    Next
    INDEX
    Explanations

    words related to death, especially sudden death, and legal proceedings around it

    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/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.58
    andoah
    -0.48
     للمعارف
    -0.47
    іга
    -0.47
     ويكيميديا
    -0.47
    ngdoc
    -0.47
    Frust
    -0.46
     GetEnumerator
    -0.45
    STACK
    -0.44
    mpro
    -0.44
    POSITIVE LOGITS
     death
    2.48
     died
    2.19
    death
    2.11
     deaths
    2.06
     dying
    1.98
     Death
    1.87
    Death
    1.84
     DEATH
    1.82
     dead
    1.81
    DEATH
    1.68
    Activations Density 1.419%

    No Known Activations