© 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. 5950
    Prev
    Next
    INDEX
    Explanations

    list items in HTML code

    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
    ']").
    -0.93
     שוליים
    -0.91
    ]").
    -0.89
    ]<<
    -0.86
    "):
    -0.82
    niająca
    -0.79
     المعيارى
    -0.78
     дописавши
    -0.78
    Geplaatst
    -0.76
    InputTagHelper
    -0.76
    POSITIVE LOGITS
    li
    1.18
    Li
    0.78
     li
    0.77
    ly
    0.71
    LI
    0.67
    Lilly
    0.67
     Li
    0.63
     Lilly
    0.60
     Lillian
    0.60
     Rossetti
    0.58
    Activations Density 0.021%

    No Known Activations