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. 23113
    Prev
    Next
    INDEX
    Explanations

    pairs of parentheses in the text

    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
     contextLoads
    -0.66
    uxxxx
    -0.63
    PropertyChanged
    -0.62
    @[+][
    -0.61
     tfsi
    -0.61
     UIFont
    -0.61
    )");
    
    -0.61
     :\\
    -0.60
     Gwen
    -0.60
     :}
    -0.59
    POSITIVE LOGITS
    Jeografia
    0.60
     huevo
    0.57
     كمان
    0.57
     Réponses
    0.56
    ñoz
    0.54
    ValueStyle
    0.54
    MockBean
    0.54
    PostConstruct
    0.54
    setDo
    0.53
    ransition
    0.53
    Activations Density 0.005%

    No Known Activations