© 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. 24-RES-MATRYOSHKA-DC
    7. 867
    Prev
    Next
    INDEX
    Explanations

    words associated with email and email clients

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     Wicidata
    -0.86
     مرئيه
    -0.82
    ंदीखरीदारी
    -0.81
     autorytatywna
    -0.80
    SceneManagement
    -0.73
    IVEREF
    -0.70
     createSprite
    -0.69
    gdx
    -0.68
     crossorigin
    -0.68
    tonsoft
    -0.66
    POSITIVE LOGITS
     email
    1.35
     mail
    1.34
     sender
    1.18
     emails
    1.16
     mailing
    1.16
    mail
    1.15
     Email
    1.11
     mails
    1.11
     Mail
    1.10
     sent
    1.09
    Activations Density 1.045%

    No Known Activations