© 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. 15259
    Prev
    Next
    INDEX
    Explanations

    hexadecimal values or codes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -0.83
    Geplaatst
    -0.77
    最快更新
    -0.68
    يميديا
    -0.66
    romycin
    -0.66
     Channing
    -0.65
    underbrace
    -0.63
    XmlEnum
    -0.62
    AsUp
    -0.61
     الدولى
    -0.61
    POSITIVE LOGITS
    polation
    0.81
    xf
    0.75
     xb
    0.71
     Nih
    0.70
    xb
    0.69
    replaceable
    0.65
    heritance
    0.64
    urethane
    0.62
     XE
    0.62
    BibitemShut
    0.62
    Activations Density 0.075%

    No Known Activations