Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19666
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mc" followed by varying context, likely related to individuals involved in legal cases or citations

    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
     Orient
    -0.85
     Dominguez
    -0.80
     링크
    -0.76
    iris
    -0.76
    CrossOrigin
    -0.73
    guenos
    -0.72
    Orient
    -0.70
    ,:]
    -0.70
    mtp
    -0.69
    '}}
    -0.68
    POSITIVE LOGITS
    Mc
    1.45
     Mc
    1.42
     McGu
    1.15
     McCar
    1.09
     mc
    1.06
     McG
    1.03
     McGregor
    1.02
     McCl
    1.02
     McCa
    1.00
     McQu
    0.96
    Activations Density 0.026%

    No Known Activations