© 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. 1667
    Prev
    Next
    INDEX
    Explanations

    biographies of people who have titles or who have been chairman of something

    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
    yaitu
    -0.65
     bhai
    -0.60
    esistenza
    -0.57
    dengar
    -0.56
    diğinde
    -0.54
     приро
    -0.53
     relâche
    -0.53
    Wahl
    -0.53
    όμε
    -0.52
    tymologie
    -0.52
    POSITIVE LOGITS
     Nigeria
    1.02
     Nigerian
    0.98
     Lagos
    0.97
     Nigerians
    0.94
    Nigeria
    0.91
    Lagos
    0.91
    Nigerian
    0.90
     Abuja
    0.89
    THISDAY
    0.85
    Niger
    0.84
    Activations Density 1.614%

    No Known Activations