© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13750
    Prev
    Next
    INDEX
    Explanations

    references to gestational age

    oai_token-act-pair · gpt-4.1-nano
    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
     referenties
    -0.60
    υμα
    -0.57
     hence
    -0.56
    Preise
    -0.56
    Lähteet
    -0.54
    PreAuthorize
    -0.54
    icide
    -0.53
    hence
    -0.53
     onResume
    -0.51
    roughs
    -0.51
    POSITIVE LOGITS
     gestational
    3.36
     Gest
    1.75
     gest
    1.66
    Gest
    1.55
    gest
    1.54
     gestation
    1.27
     GEST
    0.84
     gesta
    0.82
    تقاوى
    0.78
    GEST
    0.72
    Activations Density 0.000%

    No Known Activations