© 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. 6195
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or terms indicating the existence of structures or properties in a theoretical context

    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
    <_>
    -0.53
    ForTesting
    -0.53
     kaynağından
    -0.52
     educativas
    -0.51
    erda
    -0.48
     Coder
    -0.48
     financeiro
    -0.47
     templ
    -0.47
     défaut
    -0.46
    SequentialGroup
    -0.46
    POSITIVE LOGITS
     ſmall
    0.64
    saraba
    0.63
     itſelf
    0.61
     metav
    0.61
     modelAndView
    0.60
     oprot
    0.58
     Diſ
    0.57
    ChildScrollView
    0.57
    twimg
    0.56
    StoreMessageInfo
    0.55
    Activations Density 0.207%

    No Known Activations