© 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. 20566
    Prev
    Next
    INDEX
    Explanations

    segments of text related to changelogs or version history documentation

    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
    hoek
    -0.55
     AssemblyProduct
    -0.50
    PageIndex
    -0.46
    Into
    -0.45
    &\
    -0.44
    achio
    -0.43
     into
    -0.43
    rairie
    -0.42
    arjo
    -0.42
    жества
    -0.41
    POSITIVE LOGITS
    InvalidProtocol
    0.78
    IsContent
    0.75
    awtextra
    0.74
    typeorm
    0.72
     AttributeSet
    0.68
    HideFlags
    0.68
    клопе
    0.67
     propOrder
    0.66
    UnusedPrivate
    0.66
     Shakspeare
    0.66
    Activations Density 0.023%

    No Known Activations