© 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. 12-RES-MATRYOSHKA-DC
    7. 5768
    Prev
    Next
    INDEX
    Explanations

    numerical values or scientific notation related to measurements and orders of magnitude

    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
     virtuel
    -0.48
    nem
    -0.47
     étions
    -0.45
     almas
    -0.43
     fuori
    -0.42
     Hamb
    -0.41
    illots
    -0.41
     recommandons
    -0.40
     on
    -0.39
    ché
    -0.39
    POSITIVE LOGITS
     Réponses
    0.98
     nahilalakip
    0.97
     Савезне
    0.94
    NameInMap
    0.92
    ंदीखरीदारी
    0.90
     kasarigan
    0.85
    AutoField
    0.84
    TextWatcher
    0.84
    principalTable
    0.84
    تقاوى
    0.81
    Activations Density 0.065%

    No Known Activations