© 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. 3081
    Prev
    Next
    INDEX
    Explanations

    references to low-cost or inexpensive items

    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
     يتيمه
    -0.78
    AddTagHelper
    -0.77
    原始内容存档于
    -0.76
    potranspiration
    -0.73
    djangoproject
    -0.71
     JADX
    -0.71
    setVerticalGroup
    -0.70
    fxml
    -0.69
    bollah
    -0.69
     <=",
    -0.68
    POSITIVE LOGITS
     cheap
    2.50
     afford
    2.44
     Cheap
    2.25
    Cheap
    2.23
    cheap
    2.22
     affordable
    2.16
     cheaply
    2.02
     Afford
    1.95
     cheaper
    1.91
    afford
    1.91
    Activations Density 0.024%

    No Known Activations