© 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. 2-RES-MATRYOSHKA-DC
    7. 6977
    Prev
    Next
    INDEX
    Explanations

    references to email messages

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phone
    -1.20
    phone
    -1.04
     Phone
    -1.04
     phones
    -1.00
    Phone
    -0.99
     telephone
    -0.93
     tele
    -0.91
     teléfono
    -0.90
     téléphone
    -0.90
     PHONE
    -0.89
    POSITIVE LOGITS
     email
    2.48
    Email
    2.30
    email
    2.25
     Email
    2.22
     EMAIL
    2.14
     emails
    2.03
    EMAIL
    2.00
     emailing
    1.74
    emails
    1.72
     Emails
    1.70
    Activations Density 0.036%

    No Known Activations