© 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. 13139
    Prev
    Next
    INDEX
    Explanations

    references to a specific chemical compound or element used as a label, indicated by the activation for "ae" (which likely abbreviates "atomic element" or a similar term)

    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
    AE
    -1.00
     AE
    -0.85
     Chwiliwch
    -0.60
    withIdentifier
    -0.59
    bootstrapcdn
    -0.57
    WTS
    -0.53
    اديم
    -0.53
    NamedQuery
    -0.52
     Ac
    -0.52
    Izvori
    -0.51
    POSITIVE LOGITS
    ae
    2.00
    DoubleQuotes
    0.79
     otomatig
    0.59
    apa
    0.56
    jgl
    0.54
     Erişim
    0.54
     beginnetje
    0.54
     CURIAM
    0.53
    WithIOException
    0.53
     vira
    0.52
    Activations Density 0.001%

    No Known Activations