© 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. 22-RES-MATRYOSHKA-DC
    7. 3245
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and measurements, sometimes associated with medical information

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     must
    -0.67
    must
    -0.51
     måste
    -0.48
     müssen
    -0.47
     harus
    -0.47
    cobacterium
    -0.47
     Must
    -0.46
    Must
    -0.45
     muszą
    -0.45
    kirche
    -0.44
    POSITIVE LOGITS
    RegressionTest
    0.91
    TestingModule
    0.76
    LookAnd
    0.74
    OGND
    0.74
    EndProject
    0.71
     мәкал
    0.69
     Вікіпе
    0.66
     للمعارف
    0.66
    UserScript
    0.66
    ंदीखरीदारी
    0.65
    Activations Density 0.357%

    No Known Activations