© 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. 23466
    Prev
    Next
    INDEX
    Explanations

    instances of specific formatting or structural elements in written documents

    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
    ogueira
    -0.79
     câte
    -0.68
    rinology
    -0.68
     culoare
    -0.67
     financieras
    -0.66
    cobacterium
    -0.65
    en
    -0.65
     учет
    -0.65
     împre
    -0.64
     histamine
    -0.62
    POSITIVE LOGITS
    NameInMap
    1.02
    }]{
    0.96
    DebuggerNonUser
    0.89
    ✨:
    0.88
    ***********/
    0.85
    StructEnd
    0.84
    awtextra
    0.84
    ölker
    0.82
     OMS
    0.81
     Peel
    0.79
    Activations Density 0.001%

    No Known Activations