© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5153
    Prev
    Next
    INDEX
    Explanations

    references to violence and casualties in the context of events or actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Hochspringen
    -0.77
     beginnetje
    -0.71
     joaat
    -0.65
    jsonwebtoken
    -0.65
    ESY
    -0.65
     JFrame
    -0.64
    StructEnd
    -0.63
    issance
    -0.60
    multirow
    -0.60
    CCESS
    -0.59
    POSITIVE LOGITS
     casualties
    0.72
     fatalities
    0.68
     morts
    0.55
    wpi
    0.55
     fatality
    0.53
     opérateur
    0.52
     morti
    0.51
     hostages
    0.50
     deaths
    0.50
     jiwa
    0.48
    Activations Density 0.122%

    No Known Activations