© 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. 6860
    Prev
    Next
    INDEX
    Explanations

    references to specific members and their defined roles or functions within a system

    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
    Chham
    -0.56
    {}{
    -0.53
    any
    -0.51
    imag
    -0.50
    permum
    -0.49
    EDEFAULT
    -0.48
     celo
    -0.48
     Frequent
    -0.47
     كث
    -0.46
    TEMPO
    -0.45
    POSITIVE LOGITS
     câte
    0.85
    씩
    0.83
    ずつ
    0.81
     ciasc
    0.78
     individually
    0.77
     masing
    0.75
     each
    0.74
     jeweils
    0.74
     ciascuno
    0.74
     ognuno
    0.73
    Activations Density 0.478%

    No Known Activations