© 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. 18653
    Prev
    Next
    INDEX
    Explanations

    references to data structures or items used in context of computer algorithms

    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
    eapple
    -0.66
     Fis
    -0.61
    a
    -0.56
     ]];
    -0.56
     Ste
    -0.55
    ']?>
    -0.54
     Thi
    -0.54
     Vin
    -0.54
     Swin
    -0.52
     Kline
    -0.52
    POSITIVE LOGITS
     שוליים
    0.81
     Chwiliwch
    0.80
    UserScript
    0.76
    GOTREF
    0.75
     Truy
    0.74
    BufferException
    0.71
     للمعارف
    0.71
    MLLoader
    0.71
    Personendaten
    0.71
     Leger
    0.70
    Activations Density 0.007%

    No Known Activations