© 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. 10767
    Prev
    Next
    INDEX
    Explanations

    terms related to redundancy in data processing

    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
    EReference
    -0.82
     remarqué
    -0.71
    Portale
    -0.70
     
    -0.70
     WES
    -0.67
     Hawkes
    -0.66
    стреча
    -0.66
    NOPQRST
    -0.65
     akal
    -0.65
     scher
    -0.64
    POSITIVE LOGITS
     redundancy
    1.55
     redund
    1.49
     Redund
    1.43
    redund
    1.41
     redundant
    1.38
    Redund
    1.32
    tető
    0.70
     unnecessary
    0.69
     defaultstate
    0.68
    ancies
    0.66
    Activations Density 0.002%

    No Known Activations