© 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. 14836
    Prev
    Next
    INDEX
    Explanations

    terms related to collateral and security in financial 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
    Negative Logits
    SuppressMessage
    -0.51
    codegen
    -0.50
    ienza
    -0.49
    ism
    -0.49
    providedIn
    -0.49
     geld
    -0.47
    Initializable
    -0.46
     nhất
    -0.45
    DIS
    -0.45
     dags
    -0.45
    POSITIVE LOGITS
     surety
    0.78
     sureties
    0.70
    Personendaten
    0.68
     كومونز
    0.67
     referenties
    0.67
     للمعارف
    0.66
     فريبيس
    0.66
    PARATUS
    0.64
     خارجية
    0.60
    rety
    0.60
    Activations Density 0.011%

    No Known Activations