© 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. 748
    Prev
    Next
    INDEX
    Explanations

    people and publications related to Argentinian history and journalism, especially identifying journalists, collaborators, magazine names, and historical events.

    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
    dymyr
    -0.42
    pova
    -0.34
     Chine
    -0.34
    ètre
    -0.32
     Moscou
    -0.31
    ernsey
    -0.31
    ersburg
    -0.31
     russe
    -0.30
     Bretagne
    -0.30
     rangs
    -0.30
    POSITIVE LOGITS
    Hispanic
    0.59
     Mexicans
    0.54
     Hispanics
    0.54
     pesos
    0.54
     Obrador
    0.54
     Exacts
    0.52
     Latinos
    0.52
     Miguel
    0.52
     Juan
    0.52
     José
    0.51
    Activations Density 3.698%

    No Known Activations