© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15453
    Prev
    Next
    INDEX
    Explanations

    references to the concept of a strong or significant victory or success

    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
    __":
    -0.65
    NOPQRST
    -0.59
     cans
    -0.58
     finals
    -0.56
     Marien
    -0.56
    APTER
    -0.56
     unions
    -0.54
     stratégique
    -0.54
    hild
    -0.54
     canning
    -0.52
    POSITIVE LOGITS
     locks
    1.30
     Locks
    1.18
     triumph
    0.96
    Locks
    0.95
    locks
    0.84
    triumph
    0.74
     tresses
    0.72
    AddTagHelper
    0.67
    Triumph
    0.63
     interplay
    0.62
    Activations Density 0.003%

    No Known Activations