© 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. 1887
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to genres, categories, academic subjects or things people enjoy

    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
    とある
    -0.48
     
    -0.47
     "
    -0.47
     gesteld
    -0.45
      
    -0.45
    ↵
    -0.44
    dostęp
    -0.44
     (
    -0.44
     içi
    -0.43
     virke
    -0.42
    POSITIVE LOGITS
     emoji
    0.86
     Majefty
    0.82
     Jefus
    0.81
     infested
    0.81
     inducing
    0.79
     emojis
    0.79
     vectorstock
    0.79
     ―――――
    0.78
     Houſe
    0.77
    adpleegd
    0.77
    Activations Density 1.859%

    No Known Activations