© 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. 10872
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional connections and loyalty

    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
     المعيارى
    -1.01
     GenerationType
    -0.90
    buttonBar
    -0.85
     للمعارف
    -0.81
    AnchorStyles
    -0.80
     Italijanski
    -0.73
    PreferredItem
    -0.71
     ligiloj
    -0.71
    évaluateur
    -0.71
     AssemblyCompany
    -0.69
    POSITIVE LOGITS
    migrations
    0.54
     established
    0.48
     committed
    0.46
    basicConfig
    0.46
     commitments
    0.45
     determined
    0.44
     promised
    0.44
     set
    0.44
     réputation
    0.43
     commitment
    0.43
    Activations Density 0.191%

    No Known Activations