© 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. 17375
    Prev
    Next
    INDEX
    Explanations

    physical interactions and gestures between individuals

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.84
    contentLoaded
    -0.78
    AndEndTag
    -0.75
    脚注の使い方
    -0.70
    IUrlHelper
    -0.68
    @[+][
    -0.64
     joaat
    -0.63
    InfoWindow
    -0.63
     AspNetCore
    -0.61
    出版年
    -0.61
    POSITIVE LOGITS
    entuh
    0.57
     sendi
    0.53
     touch
    0.48
     colonna
    0.48
     Alcott
    0.47
     Felder
    0.47
    ży
    0.46
     handen
    0.45
    jago
    0.45
    TouchListener
    0.45
    Activations Density 0.014%

    No Known Activations