© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15093
    Prev
    Next
    INDEX
    Explanations

    specific chemical compound identifiers and related experimental measurements

    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
     Monfieur
    -0.64
    Datuak
    -0.60
     pleaſure
    -0.59
     unum
    -0.59
    UVWXYZ
    -0.59
     Libri
    -0.56
     kasarigan
    -0.56
     ſever
    -0.56
     houſe
    -0.55
     publiques
    -0.55
    POSITIVE LOGITS
    maxcdn
    0.85
    EventHandler
    0.80
    rar
    0.74
    resave
    0.66
    الحياه
    0.66
    aibo
    0.63
    BrowserModule
    0.63
    otheses
    0.63
    createCanvas
    0.62
    thral
    0.61
    Activations Density 0.038%

    No Known Activations