© 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. 20226
    Prev
    Next
    INDEX
    Explanations

    terms related to mediation or mediating processes 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
    Not in Any Lists

    No Comments

    Negative Logits
     Drummond
    -0.68
     Sanz
    -0.68
    ContentAlignment
    -0.59
    DockStyle
    -0.59
     sz
    -0.58
     tas
    -0.58
    kva
    -0.56
    poz
    -0.55
     Nichols
    -0.55
     fondu
    -0.55
    POSITIVE LOGITS
     mediated
    1.11
    mediated
    1.07
     mediator
    1.02
     mediators
    0.99
     mediation
    0.96
     mediate
    0.93
     mediates
    0.90
     Mediator
    0.88
    atedral
    0.87
    etate
    0.87
    Activations Density 0.009%

    No Known Activations