© 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. 17170
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases associated with scientific concepts and methods

    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
    省市镇
    -0.65
     betekenis
    -0.59
     متعلقه
    -0.55
     Whigs
    -0.54
    stateProvider
    -0.54
    bitat
    -0.51
     Hubble
    -0.50
     mohair
    -0.49
    urther
    -0.49
     Blackstone
    -0.48
    POSITIVE LOGITS
     consist
    0.69
    Hauptartikel
    0.60
     consists
    0.56
     usually
    0.56
     involves
    0.56
     involve
    0.55
     DbType
    0.55
    retweet
    0.54
    êtement
    0.54
    CONSIN
    0.53
    Activations Density 0.168%

    No Known Activations