© 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. 2473
    Prev
    Next
    INDEX
    Explanations

    the word "recommend"

    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
     CGSize
    -0.73
     guide
    -0.68
     Guide
    -0.68
    CGSize
    -0.66
     GUIDE
    -0.66
     Guides
    -0.64
     guía
    -0.61
     guides
    -0.60
    extAlignment
    -0.60
    Kaieteur
    -0.60
    POSITIVE LOGITS
     recommend
    2.75
     recommended
    2.50
     recommendation
    2.38
     recommends
    2.38
     recommending
    2.38
     Recommend
    2.38
     RECOMMEND
    2.28
    recommend
    2.28
     Recommendation
    2.13
     recommendations
    2.11
    Activations Density 0.016%

    No Known Activations