© 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. 3-RES-MATRYOSHKA-DC
    7. 1321
    Prev
    Next
    INDEX
    Explanations

    the word "take" followed by a preposition

    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
     AssemblyCulture
    -0.82
    extAlignment
    -0.80
     defaultstate
    -0.77
     Messi
    -0.74
    dhism
    -0.74
    PMS
    -0.73
    发表于
    -0.73
     cdti
    -0.72
    timis
    -0.71
     Sams
    -0.71
    POSITIVE LOGITS
    take
    2.72
     take
    2.70
    Take
    2.63
    Taking
    2.61
     Take
    2.56
     taking
    2.53
     Taking
    2.52
     taken
    2.47
    taking
    2.47
     TAKE
    2.45
    Activations Density 1.334%

    No Known Activations