© 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. 27214
    Prev
    Next
    INDEX
    Explanations

    terms related to spokesperson roles in communications

    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
     floors
    -0.57
    enaire
    -0.57
    zzar
    -0.56
    stalline
    -0.56
    ջ
    -0.53
     floor
    -0.52
    花板
    -0.52
    ifiz
    -0.51
    floors
    -0.51
     seuil
    -0.51
    POSITIVE LOGITS
     spokesman
    1.20
     Spokes
    1.05
     spokeswoman
    0.96
     spokes
    0.91
     spokespersons
    0.86
     spokesperson
    0.84
     Gabb
    0.71
     COMMUNICATIONS
    0.68
    ⓧ
    0.68
     anhänger
    0.67
    Activations Density 0.003%

    No Known Activations