© 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. 26505
    Prev
    Next
    INDEX
    Explanations

    references to corporate leadership positions, particularly CEOs

    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
    vesse
    -0.63
    ч
    -0.62
    InstanceState
    -0.61
    Injectable
    -0.58
     Kome
    -0.58
     Manch
    -0.58
     Spon
    -0.57
    ᅠ
    -0.55
    vard
    -0.54
    intérieur
    -0.54
    POSITIVE LOGITS
     CEOs
    1.39
     CEO
    1.14
    CEO
    1.03
     ceo
    1.02
     defaultstate
    0.83
    ceo
    0.82
    談社
    0.77
     Deum
    0.77
     executives
    0.75
    ByVersion
    0.74
    Activations Density 0.004%

    No Known Activations