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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5072
    Prev
    Next
    INDEX
    Explanations

    references to email and email-related concepts

    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
     Bode
    -0.64
     toys
    -0.63
    andro
    -0.63
    sten
    -0.63
    XmlAccessType
    -0.62
     ngh
    -0.61
    enskap
    -0.60
    stu
    -0.59
    atra
    -0.59
     masters
    -0.59
    POSITIVE LOGITS
     EMAIL
    1.45
     getEmail
    1.41
    Email
    1.38
    EMAIL
    1.34
     emails
    1.33
     Email
    1.30
     Emails
    1.30
     email
    1.26
    PMailer
    1.26
    setEmail
    1.24
    Activations Density 0.034%

    No Known Activations