© 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. 6-RES-MATRYOSHKA-DC
    7. 544
    Prev
    Next
    INDEX
    Explanations

    the phrase "doesn't matter"

    oai_token-act-pair · gemini-2.0-flash
    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
    !*\
    -0.61
     ExecuteAsync
    -0.56
    complexType
    -0.53
     prow
    -0.52
     elusive
    -0.52
     PopupWindow
    -0.50
     disponibilités
    -0.49
    มิ
    -0.48
    都不能
    -0.47
     insu
    -0.47
    POSITIVE LOGITS
     hoeft
    0.82
     bekym
    0.77
     preocupes
    0.76
     needn
    0.75
    dientemente
    0.72
     worry
    0.71
    不必
    0.71
     irrelevant
    0.71
     apapun
    0.71
     needless
    0.70
    Activations Density 0.688%

    No Known Activations