© 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. 22-RES-MATRYOSHKA-DC
    7. 1429
    Prev
    Next
    INDEX
    Explanations

    references to Russia, Russian people and the Soviet Union.

    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.22.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.22.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
    thâu
    -0.61
    Aktualisiert
    -0.61
     crdi
    -0.60
     Majefty
    -0.58
    кобрита
    -0.58
     муніципалі
    -0.57
    Personendaten
    -0.57
     שוליים
    -0.57
     referenties
    -0.57
     Bonita
    -0.57
    POSITIVE LOGITS
     Russian
    1.48
     Russia
    1.34
    Russian
    1.31
    Russia
    1.22
     Moscow
    1.22
     russian
    1.12
     Russians
    1.11
     RUSS
    1.11
     Soviet
    1.09
    Moscow
    1.07
    Activations Density 1.401%

    No Known Activations