© 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. 24968
    Prev
    Next
    INDEX
    Explanations

    structured data, especially in a programming or markup context

    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
     initComponents
    -0.91
    NUMX
    -0.81
    IntoConstraints
    -0.75
    GenerationType
    -0.74
     iconFacebook
    -0.73
    InputBorder
    -0.72
    ]")]
    -0.72
     itſelf
    -0.72
    dafx
    -0.70
     vapeur
    -0.70
    POSITIVE LOGITS
     numerus
    0.47
    ULTURE
    0.46
    popup
    0.46
    なた
    0.45
    how
    0.44
    nao
    0.44
    box
    0.44
    raw
    0.43
    sal
    0.43
    wear
    0.42
    Activations Density 0.159%

    No Known Activations