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. 20830
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving division

    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
    ValueStyle
    -0.66
    krä
    -0.55
     Vandal
    -0.52
     الرخصة
    -0.52
     Specimen
    -0.50
     Telex
    -0.50
    awtextra
    -0.48
     Trie
    -0.48
    sizeCache
    -0.48
    Übernach
    -0.47
    POSITIVE LOGITS
    TagMode
    0.95
     []:
    0.75
    gonic
    0.66
     chi̍t
    0.63
    Rüyada
    0.61
    Personendaten
    0.54
    بوابة
    0.53
    TLDR
    0.53
    cesz
    0.53
     EconPapers
    0.53
    Activations Density 0.005%

    No Known Activations