© 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. 6748
    Prev
    Next
    INDEX
    Explanations

    mentions of quantity or degree, specifically "to" and numerical references indicating measurements or levels

    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
    "]];
    -0.68
    ')")
    -0.55
    ";
    -0.54
    xec
    -0.54
     Chapter
    -0.53
    ]++;
    -0.51
    ₦
    -0.51
    icia
    -0.50
     semp
    -0.50
     further
    -0.50
    POSITIVE LOGITS
    ¯
    2.70
     ¯
    1.64
    ⓧ
    1.09
    ¯¯
    1.00
    ArrowToggle
    0.91
    الحياه
    0.90
     EconPapers
    0.86
    AndEndTag
    0.85
     OFDb
    0.82
    ˉ
    0.82
    Activations Density 0.001%

    No Known Activations