© 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. 20402
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to sets and their relationships

    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
     tun
    -0.51
     Dr
    -0.48
    SharedDtor
    -0.48
     Mr
    -0.47
    ook
    -0.47
    <eos>
    -0.47
     Ben
    -0.47
    dan
    -0.47
    ben
    -0.47
    くと
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.85
    IntoConstraints
    0.74
     Theſe
    0.73
    ImageContext
    0.73
     myſelf
    0.73
    MemoryWarning
    0.72
     Cæsar
    0.72
     doubtnut
    0.71
     Efq
    0.71
     purpoſe
    0.71
    Activations Density 0.049%

    No Known Activations