© 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. 22677
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational structure and employee dynamics

    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
     BoxDecoration
    -0.66
    atimes
    -0.66
     linkovi
    -0.57
     HttpNotFound
    -0.57
    ModelAdmin
    -0.57
    moveToFirst
    -0.56
    ThroughAttribute
    -0.56
    BagConstraints
    -0.56
    الحياه
    -0.56
     resourceCulture
    -0.54
    POSITIVE LOGITS
     ivelany
    0.61
    VersionUID
    0.56
     whole
    0.55
     استنادى
    0.52
    whole
    0.49
     WHOLE
    0.47
    Xna
    0.45
     ganzen
    0.45
    nior
    0.43
     entire
    0.43
    Activations Density 0.276%

    No Known Activations