Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 30715
    Prev
    Next
    INDEX
    Explanations

    terms related to legislative processes and legislation

    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
    ölkerung
    -0.63
     rug
    -0.61
    upo
    -0.60
     muka
    -0.59
     desir
    -0.59
    kanal
    -0.58
    ixer
    -0.58
     Hour
    -0.58
     *__
    -0.58
    ontrol
    -0.58
    POSITIVE LOGITS
    islative
    1.10
     LEGISL
    0.98
     Legislative
    0.97
     Legge
    0.97
     Legisl
    0.95
    Legislative
    0.91
     legislature
    0.89
     legislative
    0.88
     legisl
    0.85
     Legis
    0.84
    Activations Density 0.005%

    No Known Activations