© 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. 26459
    Prev
    Next
    INDEX
    Explanations

    references to a chairperson or individuals in leadership roles

    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
    tle
    -0.69
     المكتبه
    -0.66
    ent
    -0.66
     nd
    -0.62
    wój
    -0.62
    yte
    -0.61
    tt
    -0.58
    o
    -0.58
     nal
    -0.57
     Moll
    -0.57
    POSITIVE LOGITS
     chairmen
    1.53
     CHAIRMAN
    1.48
     CHAIR
    1.41
     Chairs
    1.39
    irmanship
    1.39
     chairs
    1.38
     Chair
    1.36
    Chairs
    1.33
     chair
    1.31
    Chair
    1.27
    Activations Density 0.007%

    No Known Activations