© 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. 3-RES-MATRYOSHKA-DC
    7. 103
    Prev
    Next
    INDEX
    Explanations

    a combination of asterisks, brackets, and quotes often used in mathematical typography

    oai_token-act-pair · gemini-2.0-flash
    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
     
    -0.85
    .
    -0.82
    '
    -0.82
    1
    -0.81
    2
    -0.81
    0
    -0.79
     A
    -0.79
    9
    -0.71
    4
    -0.70
    5
    -0.70
    POSITIVE LOGITS
    :✨
    1.36
     itſelf
    1.32
    
    1.30
     raiſ
    1.24
     purpoſe
    1.20
     myſelf
    1.20
     Houſe
    1.17
     feroit
    1.16
     ſta
    1.15
     pouvoit
    1.15
    Activations Density 8.730%

    No Known Activations