© 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. 0-RES-MATRYOSHKA-DC
    7. 11543
    Prev
    Next
    INDEX
    Explanations

    references to quantities or amounts

    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
     مرئيه
    -0.91
    دانشنامهٔ
    -0.79
    ContentAlignment
    -0.76
    Quanti
    -0.74
    quanti
    -0.74
    kháu
    -0.73
    Qty
    -0.72
    yntaxException
    -0.72
    IntoConstraints
    -0.71
     NSCoder
    -0.69
    POSITIVE LOGITS
     quantity
    1.31
     Quantity
    1.01
    quantity
    0.98
     quality
    0.74
    Quantity
    0.73
     safety
    0.63
    quality
    0.59
    Quality
    0.58
     Quality
    0.57
     disponibilités
    0.56
    Activations Density 0.002%

    No Known Activations