© 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. 29287
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables

    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
    发表于
    -0.55
    taler
    -0.46
     contemplate
    -0.42
     میز
    -0.41
    rawd
    -0.40
    bindParam
    -0.40
    InteropServices
    -0.38
    QueryParams
    -0.38
     home
    -0.38
    protoc
    -0.38
    POSITIVE LOGITS
     myſelf
    0.82
     propOrder
    0.81
     greateſt
    0.71
    RenderAtEndOf
    0.71
     beſt
    0.69
     laſt
    0.69
     كومونز
    0.67
     houſe
    0.66
     raiſ
    0.65
     ſeveral
    0.65
    Activations Density 0.158%

    No Known Activations