© 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. 15836
    Prev
    Next
    INDEX
    Explanations

    variations of letters and their repetitions in patterns

    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
     autorytatywna
    -0.69
     BBB
    -0.57
     rédu
    -0.51
     <<<<<<<<<<<<<<
    -0.50
     éto
    -0.49
    期刊论文
    -0.48
     virtuel
    -0.48
    Barg
    -0.48
    tvguidetime
    -0.47
    entista
    -0.46
    POSITIVE LOGITS
     mergeFrom
    0.66
     Italijani
    0.60
     Baillargeon
    0.58
    quiel
    0.55
    ède
    0.55
    DebuggerStep
    0.54
     Himo
    0.53
    BERTO
    0.52
    odymium
    0.52
    ModelAttribute
    0.51
    Activations Density 0.007%

    No Known Activations