© 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. 10552
    Prev
    Next
    INDEX
    Explanations

    references to unit measurements and conversion tools

    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
    WriteTagHelper
    -0.67
    requestCode
    -0.54
     صوتيه
    -0.50
     Réponses
    -0.49
    mbggenerated
    -0.48
     userSchema
    -0.48
    hskip
    -0.47
    GraphicsUnit
    -0.47
     iprot
    -0.47
     старости
    -0.47
    POSITIVE LOGITS
     instead
    1.14
     anstatt
    1.06
    instead
    1.04
     rather
    1.03
     вместо
    0.93
    rather
    0.92
    而不是
    0.90
     Instead
    0.85
    而非
    0.85
    Instead
    0.82
    Activations Density 0.573%

    No Known Activations