© 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. 10926
    Prev
    Next
    INDEX
    Explanations

    references to "hub" in various contexts related to technology or networks

    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
    Alger
    -0.80
    ANSI
    -0.77
     Woodford
    -0.76
     Heine
    -0.75
    ideos
    -0.71
    eos
    -0.71
     Haines
    -0.71
    able
    -0.70
     srs
    -0.70
     Condens
    -0.69
    POSITIVE LOGITS
     hub
    1.60
     Hub
    1.60
     hubs
    1.52
     HUB
    1.48
    hub
    1.45
    Hub
    1.42
     Hubbard
    1.39
    HUB
    1.13
     Huber
    0.95
    Hubert
    0.91
    Activations Density 0.004%

    No Known Activations