© 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. 2-RES-MATRYOSHKA-DC
    7. 5314
    Prev
    Next
    INDEX
    Explanations

    statements expressing obligation or expectation

    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
    AutoScaleMode
    -0.66
    afficheront
    -0.66
    hnia
    -0.59
    ardı
    -0.58
     indicates
    -0.56
     impra
    -0.55
    protoimpl
    -0.54
    baomidou
    -0.53
     indicated
    -0.53
    may
    -0.50
    POSITIVE LOGITS
     supposed
    2.98
    supposed
    2.75
     suppose
    2.02
     suppos
    1.76
     supposedly
    1.69
     supposes
    1.52
     supuestamente
    1.45
     purported
    1.28
     supuesto
    1.16
     Sup
    1.12
    Activations Density 0.020%

    No Known Activations