© 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. 16823
    Prev
    Next
    INDEX
    Explanations

    references to the name "Michael."

    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
    ing
    -0.73
    AppSettings
    -0.70
     Jamb
    -0.68
    :\/\/
    -0.68
    ustom
    -0.67
    koo
    -0.66
    ."</
    -0.66
     Sext
    -0.66
     Staub
    -0.66
     unsettled
    -0.66
    POSITIVE LOGITS
     Michael
    1.32
    Michael
    1.20
     Michaels
    1.16
    MICHAEL
    1.04
     MICHAEL
    1.00
    Micha
    1.00
     michael
    0.98
     Michaelis
    0.97
    michael
    0.93
     Michaela
    0.81
    Activations Density 0.011%

    No Known Activations