© 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. 16473
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings

    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
     myſelf
    -1.20
     Efq
    -1.11
     faſt
    -1.04
     Theſe
    -1.02
     Anſ
    -1.00
     صوتيه
    -0.99
     betweenstory
    -0.99
     ſind
    -0.98
     itſelf
    -0.98
     leſs
    -0.96
    POSITIVE LOGITS
    <eos>
    0.69
    :
    0.69
     I
    0.68
    ↵↵
    0.65
    .
    0.63
    ,
    0.63
     is
    0.62
    ;
    0.60
    ?
    0.59
    に関しては
    0.54
    Activations Density 0.059%

    No Known Activations