© 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. 8799
    Prev
    Next
    INDEX
    Explanations

    references to academic articles or research papers, particularly those indexed on arXiv

    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
    parsedMessage
    -1.21
    arXiv
    -1.15
     مشين
    -1.14
     <=",
    -1.07
     فريبيس
    -1.03
    TypedDataSet
    -0.96
     jspb
    -0.92
    msgTypes
    -0.91
    ValueStyle
    -0.90
    PerformLayout
    -0.88
    POSITIVE LOGITS
    面
    0.50
     Ressources
    0.47
     doors
    0.47
     surface
    0.45
     compren
    0.45
    丟
    0.44
    oh
    0.43
    preis
    0.43
    :
    0.43
    gl
    0.42
    Activations Density 0.001%

    No Known Activations