© 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. 16286
    Prev
    Next
    INDEX
    Explanations

    terms related to legal remedies and their implications

    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
     >=",
    -0.89
     Bluestacks
    -0.86
    BufferException
    -0.85
    expandindo
    -0.83
    SqlSession
    -0.81
     Elas
    -0.80
    phile
    -0.79
    zzar
    -0.79
    -------------</
    -0.79
    principalTable
    -0.79
    POSITIVE LOGITS
     Remedies
    1.38
     remedies
    1.34
     remedy
    1.20
    medies
    1.15
     Remedy
    1.15
    Remedy
    0.98
     remedied
    0.83
     veneta
    0.80
     réfugiés
    0.73
     remedio
    0.71
    Activations Density 0.003%

    No Known Activations