© 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. 30717
    Prev
    Next
    INDEX
    Explanations

    parameter declarations for methods, particularly those that include a data type followed by an array indication

    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
    évaluateur
    -0.77
    findpost
    -0.58
    errHandler
    -0.54
    🥞
    -0.53
    principalTable
    -0.52
    Jeografia
    -0.51
    商品説明
    -0.51
    adpleegd
    -0.50
    stylers
    -0.50
     дописавши
    -0.50
    POSITIVE LOGITS
    []):
    0.58
     "..\..\..\
    0.55
    alism
    0.53
    (__('
    0.53
    esto
    0.52
    ิว
    0.51
    EndProject
    0.51
    IContainer
    0.50
     Apart
    0.50
     Zand
    0.50
    Activations Density 0.003%

    No Known Activations