© 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. 11436
    Prev
    Next
    INDEX
    Explanations

    legal terms related to filing and processing lawsuits

    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
    AutoScale
    -0.57
    basicConfig
    -0.56
    OwnProperty
    -0.55
    NewReader
    -0.51
    Muffin
    -0.50
    rzost
    -0.48
    ParallelGroup
    -0.48
     OnInit
    -0.47
    prnewswire
    -0.46
    SerializedName
    -0.46
    POSITIVE LOGITS
     definately
    0.81
     certainly
    0.79
     Certainly
    0.77
    Certainly
    0.76
    certainly
    0.74
     zweifel
    0.73
     definitiv
    0.73
     definitely
    0.67
    Definitely
    0.67
     sicuramente
    0.67
    Activations Density 0.232%

    No Known Activations