© 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. 15770
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving covariance matrices and parametric relationships

    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
    WithIOException
    -1.07
    SharedDtor
    -0.96
     kaarangay
    -0.79
     nahilalakip
    -0.77
    featureID
    -0.75
    AddTagHelper
    -0.74
    parsedMessage
    -0.72
    ніципалі
    -0.70
    FieldBuilder
    -0.69
    AutoScaleMode
    -0.68
    POSITIVE LOGITS
    MetaObject
    0.53
    owan
    0.49
    甲
    0.49
    pust
    0.46
     —
    0.46
     tred
    0.46
    éraires
    0.46
    宮
    0.45
     (@
    0.45
    ff
    0.44
    Activations Density 0.234%

    No Known Activations