© 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. 6098
    Prev
    Next
    INDEX
    Explanations

    references to significant locations, organizations, or military units

    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
    +#+
    -0.82
     otomatig
    -0.64
    <?>>
    -0.63
     disambiguazione
    -0.63
     <>",
    -0.62
     चीज़ों
    -0.60
    TestTools
    -0.60
     gawas
    -0.57
    __*/
    -0.56
    InputTagHelper
    -0.56
    POSITIVE LOGITS
    ModelSerializer
    0.49
    CreateModel
    0.46
     occasional
    0.45
     artikkelen
    0.44
    つもり
    0.43
    ształ
    0.43
     [*]
    0.42
     related
    0.42
     associated
    0.42
     المعرف
    0.42
    Activations Density 0.666%

    No Known Activations