© 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. 25924
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistical representations related to study results

    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
    -0.61
    WithMany
    -0.59
     وتسجيلات
    -0.56
    続きを読む
    -0.56
     jScrollPane
    -0.55
     Egli
    -0.53
     surla
    -0.53
    NameInMap
    -0.52
    criminate
    -0.51
    ibrary
    -0.49
    POSITIVE LOGITS
    UnsafeEnabled
    0.64
    <bos>
    0.61
    ">—
    0.60
    DotNetBar
    0.59
    ForValue
    0.58
    AddTagHelper
    0.57
    ponses
    0.56
     тим
    0.55
    EndTag
    0.54
     "..\..\..\
    0.54
    Activations Density 0.023%

    No Known Activations