© 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. 15843
    Prev
    Next
    INDEX
    Explanations

    references to additional information

    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
    Diwedd
    -0.84
     تضيفلها
    -0.75
    ″]
    -0.70
    下载附件
    -0.68
    ConstraintMaker
    -0.68
    abstractmethod
    -0.66
    ksikon
    -0.66
    CreateMap
    -0.65
     Soccerway
    -0.64
     AspNetCore
    -0.64
    POSITIVE LOGITS
     disambiguazione
    0.57
     Secund
    0.55
     "..\..\..\
    0.53
     исто
    0.52
     IBA
    0.51
     Atra
    0.50
    ilirsiniz
    0.49
     benzer
    0.49
     Bolsa
    0.49
     crdi
    0.48
    Activations Density 0.009%

    No Known Activations