© 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. 16133
    Prev
    Next
    INDEX
    Explanations

    terms related to tort law and liability

    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
     Chwiliwch
    -0.71
     onCreateView
    -0.65
    queryInterface
    -0.65
     consultato
    -0.63
     Hopf
    -0.63
     ThemeData
    -0.61
     hierogly
    -0.59
    GIVEREF
    -0.58
     Chr
    -0.58
    AppCompatTheme
    -0.57
    POSITIVE LOGITS
     tort
    1.02
     Tort
    1.02
     TORT
    0.91
     tortuga
    0.86
    Tort
    0.84
    tort
    0.79
    bingen
    0.75
    ylate
    0.70
    ждую
    0.68
    uey
    0.68
    Activations Density 0.004%

    No Known Activations