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. 24379
    Prev
    Next
    INDEX
    Explanations

    references to estate management and legal terminology related to estates

    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
     StringVar
    -0.77
    riwal
    -0.76
    rowave
    -0.75
    </i>
    -0.71
    boutin
    -0.64
    MIC
    -0.62
    b
    -0.61
    i
    -0.60
    suri
    -0.60
     tetrachloride
    -0.60
    POSITIVE LOGITS
     estates
    1.36
    Estate
    1.35
     estate
    1.30
     Estate
    1.30
     ESTATE
    1.30
     Estates
    1.16
    estate
    1.09
     للاسماء
    0.96
     Houſe
    0.87
     eſt
    0.84
    Activations Density 0.009%

    No Known Activations