© 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. 30779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a method or manner of doing something

    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
     pleaſure
    -1.34
     myſelf
    -1.16
     ſche
    -1.13
     themſelves
    -1.12
     raiſ
    -1.12
     faſt
    -1.12
     ſta
    -1.10
     poffible
    -1.09
     becauſe
    -1.05
     ſever
    -1.05
    POSITIVE LOGITS
     that
    0.87
     is
    0.64
     can
    0.63
     may
    0.60
     a
    0.58
    ,
    0.56
    </h2>
    0.53
     was
    0.52
     made
    0.51
     cela
    0.51
    Activations Density 0.028%

    No Known Activations