© 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. 31864
    Prev
    Next
    INDEX
    Explanations

    references to specific actions related to auditing and investigations involving financial and corporate activities

    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
     individually
    -0.48
    qtype
    -0.48
    either
    -0.46
    anmoins
    -0.44
    pecially
    -0.44
     individuale
    -0.43
     entweder
    -0.43
     individuales
    -0.43
     väli
    -0.42
    whether
    -0.42
    POSITIVE LOGITS
     Paglinawan
    0.71
    Hentet
    0.71
     contextLoads
    0.68
    PreExecute
    0.68
    AlterField
    0.67
    LabelTagHelper
    0.66
     становника
    0.65
    !*\
    0.64
    EndContext
    0.64
    VersionUID
    0.63
    Activations Density 0.843%

    No Known Activations