© 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. 2156
    Prev
    Next
    INDEX
    Explanations

    the word "aggregate" and its variations

    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
     Lenz
    -0.63
    tvguidetime
    -0.63
    TagHelper
    -0.59
     Miles
    -0.58
    InvalidProtocol
    -0.58
    Issued
    -0.57
    }}/>
    -0.57
     Вікіпе
    -0.57
     Bevan
    -0.57
    stonia
    -0.56
    POSITIVE LOGITS
     aggregate
    2.25
     aggregates
    2.20
     Aggreg
    2.08
     Aggregate
    2.05
     aggregated
    2.03
    aggregate
    2.00
     aggregation
    1.94
     aggreg
    1.88
    aggreg
    1.85
    Aggregate
    1.85
    Activations Density 0.029%

    No Known Activations