© 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. 18244
    Prev
    Next
    INDEX
    Explanations

    mentions of data methods and operations related to thread management

    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
    parsedMessage
    -0.76
    tvguidetime
    -0.68
    ########.
    -0.65
    InitStruct
    -0.60
    ]=>
    -0.58
     surla
    -0.58
     reft
    -0.57
    sendRedirect
    -0.56
    ReusableCell
    -0.56
    ="@+
    -0.55
    POSITIVE LOGITS
    χος
    0.55
     createSlice
    0.51
    listas
    0.48
    zação
    0.47
    ExtendWith
    0.46
    OC
    0.44
    canton
    0.44
     listar
    0.44
    ustin
    0.43
    ponible
    0.43
    Activations Density 0.095%

    No Known Activations