© 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. 2781
    Prev
    Next
    INDEX
    Explanations

    the word "baby"

    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
    adri
    -0.59
     par
    -0.59
     bu
    -0.57
     Ri
    -0.55
     Jak
    -0.55
     Ellis
    -0.52
     Kola
    -0.50
     zo
    -0.49
    ỏa
    -0.49
    wikimedia
    -0.49
    POSITIVE LOGITS
     baby
    2.98
    baby
    2.89
    Baby
    2.86
     Baby
    2.81
     BABY
    2.70
     babies
    2.67
    BABY
    2.61
    babies
    2.44
     bébé
    2.41
     Babies
    2.36
    Activations Density 0.023%

    No Known Activations