© 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. 12879
    Prev
    Next
    INDEX
    Explanations

    descriptions of specific geometric shapes and relief features

    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
     Chriftian
    -0.75
     Chrift
    -0.73
     preſent
    -0.72
    ſelf
    -0.72
     Chrif
    -0.72
    argout
    -0.71
     ſche
    -0.71
     referrerpolicy
    -0.70
     myſelf
    -0.69
     Majefty
    -0.68
    POSITIVE LOGITS
     ½
    2.48
     ¼
    2.38
     ¾
    2.13
    
    0.82
    ⅛
    0.82
    ⅕
    0.82
    ⅔
    0.80
    ⅓
    0.79
     �
    0.73
    ⅙
    0.69
    Activations Density 0.002%

    No Known Activations