© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19608
    Prev
    Next
    INDEX
    Explanations

    the word "hereby."

    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
    发表于
    -0.71
     defaultstate
    -0.70
     blest
    -0.64
    WebVitals
    -0.63
     EconPapers
    -0.63
     Seeder
    -0.63
     Alat
    -0.61
    enumi
    -0.60
    imread
    -0.60
     Orig
    -0.60
    POSITIVE LOGITS
     hereby
    2.64
     thereby
    1.08
     herewith
    1.07
     herein
    0.88
     thus
    0.86
    thus
    0.66
     hence
    0.65
     ainsi
    0.64
    HKEY
    0.63
     therefore
    0.61
    Activations Density 0.001%

    No Known Activations