© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5465
    Prev
    Next
    INDEX
    Explanations

    references to media organizations, mostly news outlets

    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
    kenalkan
    -0.48
    Gilla
    -0.44
     fondu
    -0.42
     desarroll
    -0.41
     Anniversary
    -0.41
     erfaring
    -0.41
     néglig
    -0.41
    schen
    -0.40
    Hentet
    -0.40
    fiez
    -0.40
    POSITIVE LOGITS
     Times
    1.45
    Times
    1.24
     Tribune
    1.20
     Gleaner
    1.16
     TIMES
    1.12
     newspaper
    1.08
    Tribune
    1.05
    roek
    1.03
     Herald
    1.00
     Inquirer
    0.99
    Activations Density 0.379%

    No Known Activations