© 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. 1625
    Prev
    Next
    INDEX
    Explanations

    words related to editing or changing something in appearance or functionality

    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
     yoksa
    -0.57
     hauptsächlich
    -0.52
     سعی
    -0.51
     attempt
    -0.50
     primarily
    -0.49
    phens
    -0.48
     wegen
    -0.48
     основном
    -0.47
    StructEnd
    -0.47
     demais
    -0.47
    POSITIVE LOGITS
     easily
    1.61
     fácilmente
    1.50
    easily
    1.49
     facilmente
    1.38
     facilement
    1.32
    Easily
    1.27
     Easily
    1.26
     anytime
    1.25
     without
    1.24
    without
    1.17
    Activations Density 2.939%

    No Known Activations