© 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. 2-RES-MATRYOSHKA-DC
    7. 3313
    Prev
    Next
    INDEX
    Explanations

    references to subjects or participants in studies

    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
    MessageTagHelper
    -0.68
    FailureListener
    -0.68
     instructor
    -0.60
    StructEnd
    -0.59
     AssemblyCulture
    -0.59
     Drapeau
    -0.57
     staff
    -0.56
     ModelExpression
    -0.55
    tioner
    -0.54
     supplier
    -0.53
    POSITIVE LOGITS
     становника
    0.61
     ſche
    0.59
    ?')
    0.59
     pazienti
    0.56
     winters
    0.56
     myſelf
    0.55
     Arth
    0.54
     patients
    0.54
    yntaxException
    0.54
     Patients
    0.53
    Activations Density 0.470%

    No Known Activations