© 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. 3-RES-MATRYOSHKA-DC
    7. 186
    Prev
    Next
    INDEX
    Explanations

    the word "group" and its variations, often followed by a number or letter

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.79
     McE
    -0.65
    Ethio
    -0.63
     Caw
    -0.61
     scott
    -0.60
    ︎
    -0.59
    LAR
    -0.59
     étoile
    -0.59
     Thorne
    -0.59
     bug
    -0.58
    POSITIVE LOGITS
     group
    2.98
     groups
    2.86
     Groups
    2.70
     Group
    2.69
    group
    2.64
    Group
    2.58
     GROUP
    2.58
    GROUP
    2.48
    groups
    2.44
     grupo
    2.39
    Activations Density 0.965%

    No Known Activations