© 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. 18-RES-MATRYOSHKA-DC
    7. 1077
    Prev
    Next
    INDEX
    Explanations

    the word "Group" or "group," sometimes followed by a number

    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.18.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.18.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
    AndEndTag
    -0.70
     AssemblyTitle
    -0.69
    
    -0.62
    Архівовано
    -0.59
    fotografía
    -0.58
    enumi
    -0.58
     Krie
    -0.58
     Wund
    -0.57
     fati
    -0.57
    zuli
    -0.57
    POSITIVE LOGITS
     getGroup
    1.23
     Groups
    1.07
     groups
    1.07
     group
    0.90
     GROUPS
    0.90
    groups
    0.88
    Groups
    0.87
     Group
    0.85
     GROUP
    0.84
     Gruppen
    0.83
    Activations Density 0.302%

    No Known Activations