© 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. 18-RES-MATRYOSHKA-DC
    7. 1629
    Prev
    Next
    INDEX
    Explanations

    the word "log" combined with numbers or the word "on"

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.74
    ########.
    -0.71
    帖最后由
    -0.70
    tagHelperRunner
    -0.67
     CreateTagHelper
    -0.67
    queryInterface
    -0.63
     disambiguazione
    -0.62
    StoryboardSegue
    -0.61
    Personensuche
    -0.60
     AssemblyProduct
    -0.59
    POSITIVE LOGITS
     log
    1.30
     LOG
    1.27
     logs
    1.23
     Logs
    1.16
     Log
    1.15
    Slf
    1.14
    log
    1.07
    LOG
    0.98
    Log
    0.96
    getLog
    0.96
    Activations Density 0.287%

    No Known Activations