© 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. 28890
    Prev
    Next
    INDEX
    Explanations

    actions that involve systematic processes or methodologies

    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
     >=",
    -0.62
    лябин
    -0.57
    moiselle
    -0.57
    irsi
    -0.55
    sizeCache
    -0.55
     Suff
    -0.54
    nologue
    -0.54
    ApiModelProperty
    -0.54
    tonsoft
    -0.53
    queous
    -0.53
    POSITIVE LOGITS
    rzez
    0.68
    を通して
    0.59
    expandindo
    0.56
    を通じて
    0.52
     biais
    0.52
     através
    0.51
     통해
    0.51
     attraverso
    0.51
    MessageOf
    0.49
    Through
    0.49
    Activations Density 0.074%

    No Known Activations