© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13602
    Prev
    Next
    INDEX
    Explanations

    the word "beating" which indicates detection of rhythmic or pulsatile activity

    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
    SourceChecksum
    -0.74
    Geplaatst
    -0.65
    rungsseite
    -0.64
    Билгалдахарш
    -0.64
    enumi
    -0.63
    orini
    -0.61
     beaten
    -0.60
    !*\
    -0.60
    chii
    -0.56
    argout
    -0.55
    POSITIVE LOGITS
     beating
    1.78
     defeating
    0.85
    ixel
    0.77
     المعيارى
    0.71
     comeback
    0.70
    lial
    0.65
     AttributeSet
    0.63
     AssemblyCulture
    0.60
    ItemBackground
    0.59
     noi
    0.59
    Activations Density 0.010%

    No Known Activations