© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24224
    Prev
    Next
    INDEX
    Explanations

    references to material facts 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
    <sup>
    -0.59
     “
    -0.58
     awakeFromNib
    -0.56
     dimiliki
    -0.55
     A
    -0.53
    Portail
    -0.52
    encanaan
    -0.52
    “
    -0.51
    package
    -0.51
     
    -0.51
    POSITIVE LOGITS
    LookAnd
    0.86
    StructEnd
    0.85
    afficheront
    0.72
    MLLoader
    0.70
     protoimpl
    0.69
    שְׁ
    0.69
     Castile
    0.68
     Damascus
    0.68
    ที่ยว
    0.68
     Millard
    0.67
    Activations Density 0.003%

    No Known Activations