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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8702
    Prev
    Next
    INDEX
    Explanations

    references to bans or prohibitions

    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
     بيها
    -0.72
    s
    -0.67
    ertale
    -0.66
     Sich
    -0.63
    ersburg
    -0.60
     "</
    -0.60
    งาน
    -0.59
     Myster
    -0.59
    setInput
    -0.59
    mated
    -0.59
    POSITIVE LOGITS
     bans
    1.18
     Bans
    1.09
     banning
    1.03
    Bans
    1.03
     banished
    0.99
     banish
    0.97
     ban
    0.96
     Ban
    0.94
     banned
    0.93
     BAN
    0.93
    Activations Density 0.017%

    No Known Activations