© 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. 27009
    Prev
    Next
    INDEX
    Explanations

    phrases related to burdens and their impact

    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
    RUnlock
    -0.77
    UnknownFieldSet
    -0.76
     <<<<<<<<<<<<<<
    -0.71
    Jîn
    -0.69
    etCode
    -0.67
     TestBed
    -0.66
    theless
    -0.66
    Geplaatst
    -0.65
    addCriterion
    -0.65
    rillation
    -0.65
    POSITIVE LOGITS
     burden
    0.68
     burdens
    0.55
     Belastung
    0.55
    burden
    0.54
     Burden
    0.52
     stress
    0.47
     strain
    0.47
     beban
    0.47
     فشار
    0.45
     нагруз
    0.45
    Activations Density 0.104%

    No Known Activations