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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5055
    Prev
    Next
    INDEX
    Explanations

    mentions of significant historical and military battles

    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
     military
    -0.64
    发表于
    -0.60
    military
    -0.59
    __["
    -0.50
    XDECREF
    -0.49
     firebaseConfig
    -0.49
     rowspan
    -0.48
     воен
    -0.48
     ż
    -0.47
    وانه
    -0.47
    POSITIVE LOGITS
     battle
    3.11
     Battle
    2.81
    battle
    2.78
    Battle
    2.73
     BATTLE
    2.67
     battles
    2.39
    BATTLE
    2.25
     batalla
    2.14
     battled
    2.14
     bataille
    2.09
    Activations Density 0.015%

    No Known Activations