© 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. 15857
    Prev
    Next
    INDEX
    Explanations

    scientific and mathematical terms related to functions 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
    forKey
    -0.52
    Rhestr
    -0.51
    mereka
    -0.51
     Wiktionnaire
    -0.51
    AsUp
    -0.51
    FunctionFlags
    -0.47
    posób
    -0.45
    Хьажоргаш
    -0.44
     &___
    -0.44
    venser
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.90
     <<<<<<<<<<<<<<
    0.71
    TacToe
    0.65
    AndEndTag
    0.59
     parseFrom
    0.58
    complexContent
    0.57
    naden
    0.55
    shadowOffset
    0.55
    InstrumentedTest
    0.53
    +#+#
    0.52
    Activations Density 0.072%

    No Known Activations