© 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. 22-RES-MATRYOSHKA-DC
    7. 542
    Prev
    Next
    INDEX
    Explanations

    mentions of football teams

    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
     domestiques
    -0.75
     domestique
    -0.75
     purpoſe
    -0.73
    AndEndTag
    -0.69
    buttonShape
    -0.68
     houſe
    -0.65
     ſche
    -0.65
     Monfieur
    -0.64
    enumi
    -0.62
     whoſe
    -0.61
    POSITIVE LOGITS
     FC
    0.56
     lowly
    0.53
     arch
    0.51
    entown
    0.48
    paio
    0.48
     host
    0.45
     autorytatywna
    0.45
    FC
    0.45
     rivals
    0.43
     powerhouse
    0.43
    Activations Density 0.264%

    No Known Activations