© 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. 11106
    Prev
    Next
    INDEX
    Explanations

    numerical and procedural references in legal contexts

    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
    ynes
    -0.46
     value
    -0.45
     XXI
    -0.44
    quiao
    -0.41
    ateria
    -0.40
    atoria
    -0.40
     d
    -0.39
     enter
    -0.38
     RAID
    -0.38
     Value
    -0.38
    POSITIVE LOGITS
     незавершена
    1.04
     EconPapers
    0.98
    tagHelperRunner
    0.91
    XmlAccessorType
    0.91
    AutoScaleMode
    0.89
     Мексичка
    0.89
     utafitiHapana
    0.89
    OGND
    0.88
    Diweddarwch
    0.85
    SourceChecksum
    0.83
    Activations Density 0.028%

    No Known Activations