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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14514
    Prev
    Next
    INDEX
    Explanations

    mentions of a computer program named "Explorer" or references to low-energy particles and their interactions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clusal
    -0.58
    rungsseite
    -0.52
    vard
    -0.50
    dific
    -0.49
    ďaka
    -0.49
    %@",
    -0.49
    obacter
    -0.49
    cektir
    -0.49
     touch
    -0.48
    pewa
    -0.45
    POSITIVE LOGITS
     Lind
    1.04
    Lind
    0.97
     Explorer
    0.93
    Buf
    0.87
    TagMode
    0.76
     LIND
    0.75
    saraba
    0.75
     CreateTagHelper
    0.70
    explorer
    0.68
     explorer
    0.67
    Activations Density 0.005%

    No Known Activations