© 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. 0-RES-MATRYOSHKA-DC
    7. 11343
    Prev
    Next
    INDEX
    Explanations

    structures or molecules containing sulfur atoms, indicated by the repeated activation for "thio"

    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
    Cyfarwyddwr
    -0.67
    enderror
    -0.65
    forName
    -0.63
    ChildScrollView
    -0.61
    MethodManager
    -0.60
    AppMethodBeat
    -0.57
     Recuperado
    -0.57
     افتراض
    -0.57
     VY
    -0.56
    LikeLiked
    -0.56
    POSITIVE LOGITS
    thio
    3.61
     thio
    1.91
     Thio
    1.61
    rungsseite
    0.65
    <_>
    0.60
     evening
    0.53
    OWE
    0.52
     engan
    0.50
    thi
    0.49
    evening
    0.49
    Activations Density 0.002%

    No Known Activations