© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24868
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal compensations and contractual obligations

    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
    Negative Logits
    躇
    -0.52
     CreateTagHelper
    -0.47
     passaggio
    -0.44
     pass
    -0.44
     semula
    -0.43
    ostat
    -0.43
    CustomAttributes
    -0.43
     passe
    -0.43
     [*]
    -0.43
     rendre
    -0.41
    POSITIVE LOGITS
    TagMode
    0.90
     assumption
    0.79
     assuming
    0.79
     assume
    0.77
     assumes
    0.71
    PreferredItem
    0.71
     assumptions
    0.70
     ProtoMessage
    0.69
     Assumption
    0.66
    utilisons
    0.65
    Activations Density 0.246%

    No Known Activations