© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10455
    Prev
    Next
    INDEX
    Explanations

    references to email clients, particularly in relation to tasks and functions of email management systems

    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
    Negative Logits
     onCreateView
    -0.71
    MLLoader
    -0.71
    fjspx
    -0.68
    SequentialGroup
    -0.68
     Meksiku
    -0.65
    ChromeDriver
    -0.64
     ModelExpression
    -0.64
    RegistryLite
    -0.62
    ंदीखरीदारी
    -0.60
    verwijspagina
    -0.59
    POSITIVE LOGITS
     Inbox
    0.69
     caoutchouc
    0.66
    Inbox
    0.64
     interpersonal
    0.63
    inbox
    0.61
    mailbox
    0.61
     inbox
    0.60
     familiale
    0.60
     Sociale
    0.60
     smtplib
    0.60
    Activations Density 0.102%

    No Known Activations