© 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. 27044
    Prev
    Next
    INDEX
    Explanations

    CSS style properties related to the appearance and dimensions of input elements

    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
     EClass
    -0.65
     FetchType
    -0.56
    MemoryWarning
    -0.54
    PageRoute
    -0.54
     Aula
    -0.54
    NameInMap
    -0.53
     Apro
    -0.53
     Gump
    -0.50
    PageContext
    -0.49
    TextInputLayout
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.96
    AndEndTag
    0.74
    yntaxException
    0.65
    adaptiveStyles
    0.65
    はじめに
    0.64
    WriteTagHelper
    0.58
    StructEnd
    0.57
    FailureListener
    0.56
     voici
    0.54
    حوالہ
    0.50
    Activations Density 0.025%

    No Known Activations