Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 30368
    Prev
    Next
    INDEX
    Explanations

    instances of interactions or communications related to organizational or procedural 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
    énario
    -0.60
     Мексичка
    -0.57
    zsche
    -0.57
     doInBackground
    -0.55
    kegaard
    -0.53
    antMatchers
    -0.53
    basicConfig
    -0.52
    OpenHelper
    -0.52
     Roskov
    -0.51
    érature
    -0.51
    POSITIVE LOGITS
     verbally
    0.71
     fís
    0.68
     physically
    0.68
     orally
    0.68
     Physically
    0.65
     presencial
    0.64
     verbal
    0.62
     sẻ
    0.61
     oral
    0.60
     Oral
    0.59
    Activations Density 0.411%

    No Known Activations