© 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. 5851
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and classify numbers or variables based on their mathematical properties

    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
    पया
    -0.77
    ParallelGroup
    -0.67
    }=\{
    -0.65
    fromUtf
    -0.64
    ">>
    -0.62
     صوتيه
    -0.62
    μή
    -0.60
    ViewImports
    -0.60
    قسم
    -0.60
     consist
    -0.58
    POSITIVE LOGITS
     composite
    3.03
     Composite
    2.80
    composite
    2.59
    Composite
    2.47
     composites
    2.22
     Composites
    1.79
    composites
    1.77
     COMPOS
    1.66
    COMPOS
    1.46
    复合
    1.31
    Activations Density 0.007%

    No Known Activations