© 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. 10464
    Prev
    Next
    INDEX
    Explanations

    references to "words" and their usage in various contexts

    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
     becauſe
    -0.72
     zelve
    -0.72
    sphase
    -0.71
    aughter
    -0.70
     pleaſure
    -0.67
     Initialise
    -0.66
    первых
    -0.65
     rospy
    -0.65
    RegistryLite
    -0.65
     dieux
    -0.64
    POSITIVE LOGITS
     Wink
    0.65
    vers
    0.58
    ers
    0.57
    ψ
    0.55
    bote
    0.54
    0.54
     kali
    0.53
     esper
    0.53
    mata
    0.53
     Omega
    0.53
    Activations Density 0.004%

    No Known Activations